20210616.md

ArXiv cs.CV --Wed, 16 Jun 2021

1.Is this Harmful? Learning to Predict Harmfulness Ratings from Video ⬇️

Automatically identifying harmful content in video is an important task with a wide range of applications. However, due to the difficulty of collecting high-quality labels as well as demanding computational requirements, the task has not had a satisfying general approach. Typically, only small subsets of the problem are considered, such as identifying violent content. In cases where the general problem is tackled, rough approximations and simplifications are made to deal with the lack of labels and computational complexity. In this work, we identify and tackle the two main obstacles. First, we create a dataset of approximately 4000 video clips, annotated by professionals in the field. Secondly, we demonstrate that advances in video recognition enable training models on our dataset that consider the full context of the scene. We conduct an in-depth study on our modeling choices and find that we greatly benefit from combining the visual and audio modality and that pretraining on large-scale video recognition datasets and class balanced sampling further improves performance. We additionally perform a qualitative study that reveals the heavily multi-modal nature of our dataset. Our dataset will be made available upon publication.

2.Dynamic Head: Unifying Object Detection Heads with Attentions ⬇️

The complex nature of combining localization and classification in object detection has resulted in the flourished development of methods. Previous works tried to improve the performance in various object detection heads but failed to present a unified view. In this paper, we present a novel dynamic head framework to unify object detection heads with attentions. By coherently combining multiple self-attention mechanisms between feature levels for scale-awareness, among spatial locations for spatial-awareness, and within output channels for task-awareness, the proposed approach significantly improves the representation ability of object detection heads without any computational overhead. Further experiments demonstrate that the effectiveness and efficiency of the proposed dynamic head on the COCO benchmark. With a standard ResNeXt-101-DCN backbone, we largely improve the performance over popular object detectors and achieve a new state-of-the-art at 54.0 AP. Furthermore, with latest transformer backbone and extra data, we can push current best COCO result to a new record at 60.6 AP. The code will be released at this https URL.

3.Gradient Forward-Propagation for Large-Scale Temporal Video Modelling ⬇️

How can neural networks be trained on large-volume temporal data efficiently? To compute the gradients required to update parameters, backpropagation blocks computations until the forward and backward passes are completed. For temporal signals, this introduces high latency and hinders real-time learning. It also creates a coupling between consecutive layers, which limits model parallelism and increases memory consumption. In this paper, we build upon Sideways, which avoids blocking by propagating approximate gradients forward in time, and we propose mechanisms for temporal integration of information based on different variants of skip connections. We also show how to decouple computation and delegate individual neural modules to different devices, allowing distributed and parallel training. The proposed Skip-Sideways achieves low latency training, model parallelism, and, importantly, is capable of extracting temporal features, leading to more stable training and improved performance on real-world action recognition video datasets such as HMDB51, UCF101, and the large-scale Kinetics-600. Finally, we also show that models trained with Skip-Sideways generate better future frames than Sideways models, and hence they can better utilize motion cues.

4.Multi-StyleGAN: Towards Image-Based Simulation of Time-Lapse Live-Cell Microscopy ⬇️

Time-lapse fluorescent microscopy (TLFM) combined with predictive mathematical modelling is a powerful tool to study the inherently dynamic processes of life on the single-cell level. Such experiments are costly, complex and labour intensive. A complimentary approach and a step towards completely in silico experiments, is to synthesise the imagery itself. Here, we propose Multi-StyleGAN as a descriptive approach to simulate time-lapse fluorescence microscopy imagery of living cells, based on a past experiment. This novel generative adversarial network synthesises a multi-domain sequence of consecutive timesteps. We showcase Multi-StyleGAN on imagery of multiple live yeast cells in microstructured environments and train on a dataset recorded in our laboratory. The simulation captures underlying biophysical factors and time dependencies, such as cell morphology, growth, physical interactions, as well as the intensity of a fluorescent reporter protein. An immediate application is to generate additional training and validation data for feature extraction algorithms or to aid and expedite development of advanced experimental techniques such as online monitoring or control of cells.
Code and dataset is available at this https URL.

5.Generating Data Augmentation samples for Semantic Segmentation of Salt Bodies in a Synthetic Seismic Image Dataset ⬇️

Nowadays, subsurface salt body localization and delineation, also called semantic segmentation of salt bodies, are among the most challenging geophysicist tasks. Thus, identifying large salt bodies is notoriously tricky and is crucial for identifying hydrocarbon reservoirs and drill path planning. This work proposes a Data Augmentation method based on training two generative models to augment the number of samples in a seismic image dataset for the semantic segmentation of salt bodies. Our method uses deep learning models to generate pairs of seismic image patches and their respective salt masks for the Data Augmentation. The first model is a Variational Autoencoder and is responsible for generating patches of salt body masks. The second is a Conditional Normalizing Flow model, which receives the generated masks as inputs and generates the associated seismic image patches. We evaluate the proposed method by comparing the performance of ten distinct state-of-the-art models for semantic segmentation, trained with and without the generated augmentations, in a dataset from two synthetic seismic images. The proposed methodology yields an average improvement of 8.57% in the IoU metric across all compared models. The best result is achieved by a DeeplabV3+ model variant, which presents an IoU score of 95.17% when trained with our augmentations. Additionally, our proposal outperformed six selected data augmentation methods, and the most significant improvement in the comparison, of 9.77%, is achieved by composing our DA with augmentations from an elastic transformation. At last, we show that the proposed method is adaptable for a larger context size by achieving results comparable to the obtained on the smaller context size.

6.Multi-script Handwritten Digit Recognition Using Multi-task Learning ⬇️

Handwritten digit recognition is one of the extensively studied area in machine learning. Apart from the wider research on handwritten digit recognition on MNIST dataset, there are many other research works on various script recognition. However, it is not very common for multi-script digit recognition which encourage the development of robust and multipurpose systems. Additionally working on multi-script digit recognition enables multi-task learning, considering the script classification as a related task for instance. It is evident that multi-task learning improves model performance through inductive transfer using the information contained in related tasks. Therefore, in this study multi-script handwritten digit recognition using multi-task learning will be investigated. As a specific case of demonstrating the solution to the problem, Amharic handwritten character recognition will also be experimented. The handwritten digits of three scripts including Latin, Arabic and Kannada are studied to show that multi-task models with reformulation of the individual tasks have shown promising results. In this study a novel way of using the individual tasks predictions was proposed to help classification performance and regularize the different loss for the purpose of the main task. This finding has outperformed the baseline and the conventional multi-task learning models. More importantly, it avoided the need for weighting the different losses of the tasks, which is one of the challenges in multi-task learning.

7.Towards Total Recall in Industrial Anomaly Detection ⬇️

Being able to spot defective parts is a critical component in large-scale industrial manufacturing. A particular challenge that we address in this work is the cold-start problem: fit a model using nominal (non-defective) example images only. While handcrafted solutions per class are possible, the goal is to build systems that work well simultaneously on many different tasks automatically. The best peforming approaches combine embeddings from ImageNet models with an outlier detection model. In this paper, we extend on this line of work and propose PatchCore, which uses a maximally representative memory bank of nominal patch-features. PatchCore offers competitive inference times while achieving state-of-the-art performance for both detection and localization. On the standard dataset MVTec AD, PatchCore achieves an image-level anomaly detection AUROC score of $99.1%$, more than halving the error compared to the next best competitor. We further report competitive results on two additional datasets and also find competitive results in the few samples regime.

8.BEiT: BERT Pre-Training of Image Transformers ⬇️

We introduce a self-supervised vision representation model BEiT, which stands for Bidirectional Encoder representation from Image Transformers. Following BERT developed in the natural language processing area, we propose a masked image modeling task to pretrain vision Transformers. Specifically, each image has two views in our pre-training, i.e, image patches (such as 16x16 pixels), and visual tokens (i.e., discrete tokens). We first "tokenize" the original image into visual tokens. Then we randomly mask some image patches and fed them into the backbone Transformer. The pre-training objective is to recover the original visual tokens based on the corrupted image patches. After pre-training BEiT, we directly fine-tune the model parameters on downstream tasks by appending task layers upon the pretrained encoder. Experimental results on image classification and semantic segmentation show that our model achieves competitive results with previous pre-training methods. For example, base-size BEiT achieves 83.2% top-1 accuracy on ImageNet-1K, significantly outperforming from-scratch DeiT training (81.8%) with the same setup. Moreover, large-size BEiT obtains 86.3% only using ImageNet-1K, even outperforming ViT-L with supervised pre-training on ImageNet-22K (85.2%). The code and pretrained models are available at this https URL.

9.Spot the Difference: Topological Anomaly Detection via Geometric Alignment ⬇️

Geometric alignment appears in a variety of applications, ranging from domain adaptation, optimal transport, and normalizing flows in machine learning; optical flow and learned augmentation in computer vision and deformable registration within biomedical imaging. A recurring challenge is the alignment of domains whose topology is not the same; a problem that is routinely ignored, potentially introducing bias in downstream analysis. As a first step towards solving such alignment problems, we propose an unsupervised topological difference detection algorithm. The model is based on a conditional variational auto-encoder and detects topological anomalies with regards to a reference alongside the registration step. We consider both a) topological changes in the image under spatial variation and b) unexpected transformations. Our approach is validated on a proxy task of unsupervised anomaly detection in images.

10.A Spacecraft Dataset for Detection, Segmentation and Parts Recognition ⬇️

Virtually all aspects of modern life depend on space technology. Thanks to the great advancement of computer vision in general and deep learning-based techniques in particular, over the decades, the world witnessed the growing use of deep learning in solving problems for space applications, such as self-driving robot, tracers, insect-like robot on cosmos and health monitoring of spacecraft. These are just some prominent examples that has advanced space industry with the help of deep learning. However, the success of deep learning models requires a lot of training data in order to have decent performance, while on the other hand, there are very limited amount of publicly available space datasets for the training of deep learning models. Currently, there is no public datasets for space-based object detection or instance segmentation, partly because manually annotating object segmentation masks is very time consuming as they require pixel-level labelling, not to mention the challenge of obtaining images from space. In this paper, we aim to fill this gap by releasing a dataset for spacecraft detection, instance segmentation and part recognition. The main contribution of this work is the development of the dataset using images of space stations and satellites, with rich annotations including bounding boxes of spacecrafts and masks to the level of object parts, which are obtained with a mixture of automatic processes and manual efforts. We also provide evaluations with state-of-the-art methods in object detection and instance segmentation as a benchmark for the dataset. The link for downloading the proposed dataset can be found on this https URL.

11.Weakly-Supervised Photo-realistic Texture Generation for 3D Face Reconstruction ⬇️

Although much progress has been made recently in 3D face reconstruction, most previous work has been devoted to predicting accurate and fine-grained 3D shapes. In contrast, relatively little work has focused on generating high-fidelity face textures. Compared with the prosperity of photo-realistic 2D face image generation, high-fidelity 3D face texture generation has yet to be studied. In this paper, we proposed a novel UV map generation model that predicts the UV map from a single face image. The model consists of a UV sampler and a UV generator. By selectively sampling the input face image's pixels and adjusting their relative locations, the UV sampler generates an incomplete UV map that could faithfully reconstruct the original face. Missing textures in the incomplete UV map are further full-filled by the UV generator. The training is based on pseudo ground truth blended by the 3DMM texture and the input face texture, thus weakly supervised. To deal with the artifacts in the imperfect pseudo UV map, multiple partial UV map discriminators are leveraged.

12.Generating Thermal Human Faces for Physiological Assessment Using Thermal Sensor Auxiliary Labels ⬇️

Thermal images reveal medically important physiological information about human stress, signs of inflammation, and emotional mood that cannot be seen on visible images. Providing a method to generate thermal faces from visible images would be highly valuable for the telemedicine community in order to show this medical information. To the best of our knowledge, there are limited works on visible-to-thermal (VT) face translation, and many current works go the opposite direction to generate visible faces from thermal surveillance images (TV) for law enforcement applications. As a result, we introduce favtGAN, a VT GAN which uses the pix2pix image translation model with an auxiliary sensor label prediction network for generating thermal faces from visible images. Since most TV methods are trained on only one data source drawn from one thermal sensor, we combine datasets from faces and cityscapes. These combined data are captured from similar sensors in order to bootstrap the training and transfer learning task, especially valuable because visible-thermal face datasets are limited. Experiments on these combined datasets show that favtGAN demonstrates an increase in SSIM and PSNR scores of generated thermal faces, compared to training on a single face dataset alone.

13.Computer-aided Interpretable Features for Leaf Image Classification ⬇️

Plant species identification is time consuming, costly, and requires lots of efforts, and expertise knowledge. In recent, many researchers use deep learning methods to classify plants directly using plant images. While deep learning models have achieved a great success, the lack of interpretability limit their widespread application. To overcome this, we explore the use of interpretable, measurable and computer-aided features extracted from plant leaf images. Image processing is one of the most challenging, and crucial steps in feature-extraction. The purpose of image processing is to improve the leaf image by removing undesired distortion. The main image processing steps of our algorithm involves: i) Convert original image to RGB (Red-Green-Blue) image, ii) Gray scaling, iii) Gaussian smoothing, iv) Binary thresholding, v) Remove stalk, vi) Closing holes, and vii) Resize image. The next step after image processing is to extract features from plant leaf images. We introduced 52 computationally efficient features to classify plant species. These features are mainly classified into four groups as: i) shape-based features, ii) color-based features, iii) texture-based features, and iv) scagnostic features. Length, width, area, texture correlation, monotonicity and scagnostics are to name few of them. We explore the ability of features to discriminate the classes of interest under supervised learning and unsupervised learning settings. For that, supervised dimensionality reduction technique, Linear Discriminant Analysis (LDA), and unsupervised dimensionality reduction technique, Principal Component Analysis (PCA) are used to convert and visualize the images from digital-image space to feature space. The results show that the features are sufficient to discriminate the classes of interest under both supervised and unsupervised learning settings.

14.Mutation Sensitive Correlation Filter for Real-Time UAV Tracking with Adaptive Hybrid Label ⬇️

Unmanned aerial vehicle (UAV) based visual tracking has been confronted with numerous challenges, e.g., object motion and occlusion. These challenges generally introduce unexpected mutations of target appearance and result in tracking failure. However, prevalent discriminative correlation filter (DCF) based trackers are insensitive to target mutations due to a predefined label, which concentrates on merely the centre of the training region. Meanwhile, appearance mutations caused by occlusion or similar objects usually lead to the inevitable learning of wrong information. To cope with appearance mutations, this paper proposes a novel DCF-based method to enhance the sensitivity and resistance to mutations with an adaptive hybrid label, i.e., MSCF. The ideal label is optimized jointly with the correlation filter and remains temporal consistency. Besides, a novel measurement of mutations called mutation threat factor (MTF) is applied to correct the label dynamically. Considerable experiments are conducted on widely used UAV benchmarks. The results indicate that the performance of MSCF tracker surpasses other 26 state-of-the-art DCF-based and deep-based trackers. With a real-time speed of _38 frames/s, the proposed approach is sufficient for UAV tracking commissions.

15.Relation Modeling in Spatio-Temporal Action Localization ⬇️

This paper presents our solution to the AVA-Kinetics Crossover Challenge of ActivityNet workshop at CVPR 2021. Our solution utilizes multiple types of relation modeling methods for spatio-temporal action detection and adopts a training strategy to integrate multiple relation modeling in end-to-end training over the two large-scale video datasets. Learning with memory bank and finetuning for long-tailed distribution are also investigated to further improve the performance. In this paper, we detail the implementations of our solution and provide experiments results and corresponding discussions. We finally achieve 40.67 mAP on the test set of AVA-Kinetics.

16.Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Camera ⬇️

We present a novel method for real-time pose and shape reconstruction of two strongly interacting hands. Our approach is the first two-hand tracking solution that combines an extensive list of favorable properties, namely it is marker-less, uses a single consumer-level depth camera, runs in real time, handles inter- and intra-hand collisions, and automatically adjusts to the user's hand shape. In order to achieve this, we embed a recent parametric hand pose and shape model and a dense correspondence predictor based on a deep neural network into a suitable energy minimization framework. For training the correspondence prediction network, we synthesize a two-hand dataset based on physical simulations that includes both hand pose and shape annotations while at the same time avoiding inter-hand penetrations. To achieve real-time rates, we phrase the model fitting in terms of a nonlinear least-squares problem so that the energy can be optimized based on a highly efficient GPU-based Gauss-Newton optimizer. We show state-of-the-art results in scenes that exceed the complexity level demonstrated by previous work, including tight two-hand grasps, significant inter-hand occlusions, and gesture interaction.

17.Demographic Fairness in Face Identification: The Watchlist Imbalance Effect ⬇️

Recently, different researchers have found that the gallery composition of a face database can induce performance differentials to facial identification systems in which a probe image is compared against up to all stored reference images to reach a biometric decision. This negative effect is referred to as "watchlist imbalance effect". In this work, we present a method to theoretically estimate said effect for a biometric identification system given its verification performance across demographic groups and the composition of the used gallery. Further, we report results for identification experiments on differently composed demographic subsets, i.e. females and males, of the public academic MORPH database using the open-source ArcFace face recognition system. It is shown that the database composition has a huge impact on performance differentials in biometric identification systems, even if performance differentials are less pronounced in the verification scenario. This study represents the first detailed analysis of the watchlist imbalance effect which is expected to be of high interest for future research in the field of facial recognition.

18.Object detection and Autoencoder-based 6D pose estimation for highly cluttered Bin Picking ⬇️

Bin picking is a core problem in industrial environments and robotics, with its main module as 6D pose estimation. However, industrial depth sensors have a lack of accuracy when it comes to small objects. Therefore, we propose a framework for pose estimation in highly cluttered scenes with small objects, which mainly relies on RGB data and makes use of depth information only for pose refinement. In this work, we compare synthetic data generation approaches for object detection and pose estimation and introduce a pose filtering algorithm that determines the most accurate estimated poses. We will make our

19.Hotel Recognition via Latent Image Embedding ⬇️

We approach the problem of hotel recognition with deep metric learning. We overview the existing approaches and propose a modification to Contrastive loss called Contrastive-Triplet loss. We construct a robust pipeline for benchmarking metric learning models and perform experiments on Hotels-50K and CUB200 datasets. Contrastive-Triplet loss is shown to achieve better retrieval on Hotels-50k. We open-source our code.

20.A Clinically Inspired Approach for Melanoma classification ⬇️

Melanoma is a leading cause of deaths due to skin cancer deaths and hence, early and effective diagnosis of melanoma is of interest. Current approaches for automated diagnosis of melanoma either use pattern recognition or analytical recognition like ABCDE (asymmetry, border, color, diameter and evolving) criterion. In practice however, a differential approach wherein outliers (ugly duckling) are detected and used to evaluate nevi/lesions. Incorporation of differential recognition in Computer Aided Diagnosis (CAD) systems has not been explored but can be beneficial as it can provide a clinical justification for the derived decision. We present a method for identifying and quantifying ugly ducklings by performing Intra-Patient Comparative Analysis (IPCA) of neighboring nevi. This is then incorporated in a CAD system design for melanoma detection. This design ensures flexibility to handle cases where IPCA is not possible. Our experiments on a public dataset show that the outlier information helps boost the sensitivity of detection by at least 4.1 % and specificity by 4.0 % to 8.9 %, depending on the use of a strong (EfficientNet) or moderately strong (VGG or ResNet) classifier.

21.Color2Style: Real-Time Exemplar-Based Image Colorization with Self-Reference Learning and Deep Feature Modulation ⬇️

Legacy black-and-white photos are riddled with people's nostalgia and glorious memories of the past. To better relive the elapsed frozen moments, in this paper, we present a deep exemplar-based image colorization approach named Color2Style to resurrect these grayscale image media by filling them with vibrant colors. Generally, for exemplar-based colorization, unsupervised and unpaired training are usually adopted, due to the difficulty of obtaining input and ground truth image pairs. To train an exemplar-based colorization model, current algorithms usually strive to achieve two procedures: i) retrieving a large number of reference images with high similarity in advance, which is inevitably time-consuming and tedious; ii) designing complicated modules to transfer the colors of the reference image to the grayscale image, by calculating and leveraging the deep semantic correspondence between them (e.g., non-local operation). Contrary to the previous methods, we solve and simplify the above two steps in one end-to-end learning procedure. First, we adopt a self-augmented self-reference training scheme, where the reference image is generated by graphical transformations from the original colorful one whereby the training can be formulated in a paired manner. Second, instead of computing complex and inexplicable correspondence maps, our method exploits a simple yet effective deep feature modulation (DFM) module, which injects the color embeddings extracted from the reference image into the deep representations of the input grayscale image. Such design is much more lightweight and intelligible, achieving appealing performance with real-time processing speed. Moreover, our model does not require multifarious loss functions and regularization terms like existing methods, but only two widely used loss functions. Codes and models will be available at this https URL.

22.Compositional Sketch Search ⬇️

We present an algorithm for searching image collections using free-hand sketches that describe the appearance and relative positions of multiple objects. Sketch based image retrieval (SBIR) methods predominantly match queries containing a single, dominant object invariant to its position within an image. Our work exploits drawings as a concise and intuitive representation for specifying entire scene compositions. We train a convolutional neural network (CNN) to encode masked visual features from sketched objects, pooling these into a spatial descriptor encoding the spatial relationships and appearances of objects in the composition. Training the CNN backbone as a Siamese network under triplet loss yields a metric search embedding for measuring compositional similarity which may be efficiently leveraged for visual search by applying product quantization.

23.SAR Image Classification Based on Spiking Neural Network through Spike-Time Dependent Plasticity and Gradient Descent ⬇️

At present, the Synthetic Aperture Radar (SAR) image classification method based on convolution neural network (CNN) has faced some problems such as poor noise resistance and generalization ability. Spiking neural network (SNN) is one of the core components of brain-like intelligence and has good application prospects. This article constructs a complete SAR image classifier based on unsupervised and supervised learning of SNN by using spike sequences with complex spatio-temporal information. We firstly expound the spiking neuron model, the receptive field of SNN, and the construction of spike sequence. Then we put forward an unsupervised learning algorithm based on STDP and a supervised learning algorithm based on gradient descent. The average classification accuracy of single layer and bilayer unsupervised learning SNN in three categories images on MSTAR dataset is 80.8% and 85.1%, respectively. Furthermore, the convergent output spike sequences of unsupervised learning can be used as teaching signals. Based on the TensorFlow framework, a single layer supervised learning SNN is built from the bottom, and the classification accuracy reaches 90.05%. By comparing noise resistance and model parameters between SNNs and CNNs, the effectiveness and outstanding advantages of SNN are verified. Code to reproduce our experiments is available at \url{this https URL}.

24.Zero-sample surface defect detection and classification based on semantic feedback neural network ⬇️

Defect detection and classification technology has changed from traditional artificial visual inspection to current intelligent automated inspection, but most of the current defect detection methods are training related detection models based on a data-driven approach, taking into account the difficulty of collecting some sample data in the industrial field. We apply zero-shot learning technology to the industrial field. Aiming at the problem of the existing "Latent Feature Guide Attribute Attention" (LFGAA) zero-shot image classification network, the output latent attributes and artificially defined attributes are different in the semantic space, which leads to the problem of model performance degradation, proposed an LGFAA network based on semantic feedback, and improved model performance by constructing semantic embedded modules and feedback mechanisms. At the same time, for the common domain shift problem in zero-shot learning, based on the idea of co-training algorithm using the difference information between different views of data to learn from each other, we propose an Ensemble Co-training algorithm, which adaptively reduces the prediction error in image tag embedding from multiple angles. Various experiments conducted on the zero-shot dataset and the cylinder liner dataset in the industrial field provide competitive results.

25.Cascading Convolutional Temporal Colour Constancy ⬇️

Computational Colour Constancy (CCC) consists of estimating the colour of one or more illuminants in a scene and using them to remove unwanted chromatic distortions. Much research has focused on illuminant estimation for CCC on single images, with few attempts of leveraging the temporal information intrinsic in sequences of correlated images (e.g., the frames in a video), a task known as Temporal Colour Constancy (TCC). The state-of-the-art for TCC is TCCNet, a deep-learning architecture that uses a ConvLSTM for aggregating the encodings produced by CNN submodules for each image in a sequence. We extend this architecture with different models obtained by (i) substituting the TCCNet submodules with C4, the state-of-the-art method for CCC targeting images; (ii) adding a cascading strategy to perform an iterative improvement of the estimate of the illuminant. We tested our models on the recently released TCC benchmark and achieved results that surpass the state-of-the-art. Analyzing the impact of the number of frames involved in illuminant estimation on performance, we show that it is possible to reduce inference time by training the models on few selected frames from the sequences while retaining comparable accuracy.

26.Direction-aware Feature-level Frequency Decomposition for Single Image Deraining ⬇️

We present a novel direction-aware feature-level frequency decomposition network for single image deraining. Compared with existing solutions, the proposed network has three compelling characteristics. First, unlike previous algorithms, we propose to perform frequency decomposition at feature-level instead of image-level, allowing both low-frequency maps containing structures and high-frequency maps containing details to be continuously refined during the training procedure. Second, we further establish communication channels between low-frequency maps and high-frequency maps to interactively capture structures from high-frequency maps and add them back to low-frequency maps and, simultaneously, extract details from low-frequency maps and send them back to high-frequency maps, thereby removing rain streaks while preserving more delicate features in the input image. Third, different from existing algorithms using convolutional filters consistent in all directions, we propose a direction-aware filter to capture the direction of rain streaks in order to more effectively and thoroughly purge the input images of rain streaks. We extensively evaluate the proposed approach in three representative datasets and experimental results corroborate our approach consistently outperforms state-of-the-art deraining algorithms.

27.Image Feature Information Extraction for Interest Point Detection: A Comprehensive Review ⬇️

Interest point detection is one of the most fundamental and critical problems in computer vision and image processing. In this paper, we carry out a comprehensive review on image feature information (IFI) extraction techniques for interest point detection. To systematically introduce how the existing interest point detection methods extract IFI from an input image, we propose a taxonomy of the IFI extraction techniques for interest point detection. According to this taxonomy, we discuss different types of IFI extraction techniques for interest point detection. Furthermore, we identify the main unresolved issues related to the existing IFI extraction techniques for interest point detection and any interest point detection methods that have not been discussed before. The existing popular datasets and evaluation standards are provided and the performances for eighteen state-of-the-art approaches are evaluated and discussed. Moreover, future research directions on IFI extraction techniques for interest point detection are elaborated.

28.ReS2tAC -- UAV-Borne Real-Time SGM Stereo Optimized for Embedded ARM and CUDA Devices ⬇️

With the emergence of low-cost robotic systems, such as unmanned aerial vehicle, the importance of embedded high-performance image processing has increased. For a long time, FPGAs were the only processing hardware that were capable of high-performance computing, while at the same time preserving a low power consumption, essential for embedded systems. However, the recently increasing availability of embedded GPU-based systems, such as the NVIDIA Jetson series, comprised of an ARM CPU and a NVIDIA Tegra GPU, allows for massively parallel embedded computing on graphics hardware. With this in mind, we propose an approach for real-time embedded stereo processing on ARM and CUDA-enabled devices, which is based on the popular and widely used Semi-Global Matching algorithm. In this, we propose an optimization of the algorithm for embedded CUDA GPUs, by using massively parallel computing, as well as using the NEON intrinsics to optimize the algorithm for vectorized SIMD processing on embedded ARM CPUs. We have evaluated our approach with different configurations on two public stereo benchmark datasets to demonstrate that they can reach an error rate as low as 3.3%. Furthermore, our experiments show that the fastest configuration of our approach reaches up to 46 FPS on VGA image resolution. Finally, in a use-case specific qualitative evaluation, we have evaluated the power consumption of our approach and deployed it on the DJI Manifold 2-G attached to a DJI Matrix 210v2 RTK unmanned aerial vehicle (UAV), demonstrating its suitability for real-time stereo processing onboard a UAV.

29.Encouraging Intra-Class Diversity Through a Reverse Contrastive Loss for Better Single-Source Domain Generalization ⬇️

Traditional deep learning algorithms often fail to generalize when they are tested outside of the domain of training data. Because data distributions can change dynamically in real-life applications once a learned model is deployed, in this paper we are interested in single-source domain generalization (SDG) which aims to develop deep learning algorithms able to generalize from a single training domain where no information about the test domain is available at training time. Firstly, we design two simple MNISTbased SDG benchmarks, namely MNIST Color SDG-MP and MNIST Color SDG-UP, which highlight the two different fundamental SDG issues of increasing difficulties: 1) a class-correlated pattern in the training domain is missing (SDG-MP), or 2) uncorrelated with the class (SDG-UP), in the testing data domain. This is in sharp contrast with the current domain generalization (DG) benchmarks which mix up different correlation and variation factors and thereby make hard to disentangle success or failure factors when benchmarking DG algorithms. We further evaluate several state-of-the-art SDG algorithms through our simple benchmark, namely MNIST Color SDG-MP, and show that the issue SDG-MP is largely unsolved despite of a decade of efforts in developing DG algorithms. Finally, we also propose a partially reversed contrastive loss to encourage intra-class diversity and find less strongly correlated patterns, to deal with SDG-MP and show that the proposed approach is very effective on our MNIST Color SDG-MP benchmark.

30.Mixed Model OCR Training on Historical Latin Script for Out-of-the-Box Recognition and Finetuning ⬇️

In order to apply Optical Character Recognition (OCR) to historical printings of Latin script fully automatically, we report on our efforts to construct a widely-applicable polyfont recognition model yielding text with a Character Error Rate (CER) around 2% when applied out-of-the-box. Moreover, we show how this model can be further finetuned to specific classes of printings with little manual and computational effort. The mixed or polyfont model is trained on a wide variety of materials, in terms of age (from the 15th to the 19th century), typography (various types of Fraktur and Antiqua), and languages (among others, German, Latin, and French). To optimize the results we combined established techniques of OCR training like pretraining, data augmentation, and voting. In addition, we used various preprocessing methods to enrich the training data and obtain more robust models. We also implemented a two-stage approach which first trains on all available, considerably unbalanced data and then refines the output by training on a selected more balanced subset. Evaluations on 29 previously unseen books resulted in a CER of 1.73%, outperforming a widely used standard model with a CER of 2.84% by almost 40%. Training a more specialized model for some unseen Early Modern Latin books starting from our mixed model led to a CER of 1.47%, an improvement of up to 50% compared to training from scratch and up to 30% compared to training from the aforementioned standard model. Our new mixed model is made openly available to the community.

31.Vision-Language Navigation with Random Environmental Mixup ⬇️

Vision-language Navigation (VLN) tasks require an agent to navigate step-by-step while perceiving the visual observations and comprehending a natural language instruction. Large data bias, which is caused by the disparity ratio between the small data scale and large navigation space, makes the VLN task challenging. Previous works have proposed various data augmentation methods to reduce data bias. However, these works do not explicitly reduce the data bias across different house scenes. Therefore, the agent would overfit to the seen scenes and achieve poor navigation performance in the unseen scenes. To tackle this problem, we propose the Random Environmental Mixup (REM) method, which generates cross-connected house scenes as augmented data via mixuping environment. Specifically, we first select key viewpoints according to the room connection graph for each scene. Then, we cross-connect the key views of different scenes to construct augmented scenes. Finally, we generate augmented instruction-path pairs in the cross-connected scenes. The experimental results on benchmark datasets demonstrate that our augmentation data via REM help the agent reduce its performance gap between the seen and unseen environment and improve the overall performance, making our model the best existing approach on the standard VLN benchmark.

32.Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images ⬇️

State-of-the-art (SOTA) Generative Models (GMs) can synthesize photo-realistic images that are hard for humans to distinguish from genuine photos. We propose to perform reverse engineering of GMs to infer the model hyperparameters from the images generated by these models. We define a novel problem, "model parsing", as estimating GM network architectures and training loss functions by examining their generated images -- a task seemingly impossible for human beings. To tackle this problem, we propose a framework with two components: a Fingerprint Estimation Network (FEN), which estimates a GM fingerprint from a generated image by training with four constraints to encourage the fingerprint to have desired properties, and a Parsing Network (PN), which predicts network architecture and loss functions from the estimated fingerprints. To evaluate our approach, we collect a fake image dataset with $100$K images generated by $100$ GMs. Extensive experiments show encouraging results in parsing the hyperparameters of the unseen models. Finally, our fingerprint estimation can be leveraged for deepfake detection and image attribution, as we show by reporting SOTA results on both the recent Celeb-DF and image attribution benchmarks.

33.Domain Adaptive SiamRPN++ for Object Tracking in the Wild ⬇️

Benefit from large-scale training data, recent advances in Siamese-based object tracking have achieved compelling results on the normal sequences. Whilst Siamese-based trackers assume training and test data follow an identical distribution. Suppose there is a set of foggy or rainy test sequences, it cannot be guaranteed that the trackers trained on the normal images perform well on the data belonging to other domains. The problem of domain shift among training and test data has already been discussed in object detection and semantic segmentation areas, which, however, has not been investigated for visual tracking. To this end, based on SiamRPN++, we introduce a Domain Adaptive SiamRPN++, namely DASiamRPN++, to improve the cross-domain transferability and robustness of a tracker. Inspired by A-distance theory, we present two domain adaptive modules, Pixel Domain Adaptation (PDA) and Semantic Domain Adaptation (SDA). The PDA module aligns the feature maps of template and search region images to eliminate the pixel-level domain shift caused by weather, illumination, etc. The SDA module aligns the feature representations of the tracking target's appearance to eliminate the semantic-level domain shift. PDA and SDA modules reduce the domain disparity by learning domain classifiers in an adversarial training manner. The domain classifiers enforce the network to learn domain-invariant feature representations. Extensive experiments are performed on the standard datasets of two different domains, including synthetic foggy and TIR sequences, which demonstrate the transferability and domain adaptability of the proposed tracker.

34.Keep CALM and Improve Visual Feature Attribution ⬇️

The class activation mapping, or CAM, has been the cornerstone of feature attribution methods for multiple vision tasks. Its simplicity and effectiveness have led to wide applications in the explanation of visual predictions and weakly-supervised localization tasks. However, CAM has its own shortcomings. The computation of attribution maps relies on ad-hoc calibration steps that are not part of the training computational graph, making it difficult for us to understand the real meaning of the attribution values. In this paper, we improve CAM by explicitly incorporating a latent variable encoding the location of the cue for recognition in the formulation, thereby subsuming the attribution map into the training computational graph. The resulting model, class activation latent mapping, or CALM, is trained with the expectation-maximization algorithm. Our experiments show that CALM identifies discriminative attributes for image classifiers more accurately than CAM and other visual attribution baselines. CALM also shows performance improvements over prior arts on the weakly-supervised object localization benchmarks. Our code is available at this https URL.

35.A Hybrid mmWave and Camera System for Long-Range Depth Imaging ⬇️

mmWave radars offer excellent depth resolution owing to their high bandwidth at mmWave radio frequencies. Yet, they suffer intrinsically from poor angular resolution, that is an order-of-magnitude worse than camera systems, and are therefore not a capable 3-D imaging solution in isolation. We propose Metamoran, a system that combines the complimentary strengths of radar and camera systems to obtain depth images at high azimuthal resolutions at distances of several tens of meters with high accuracy, all from a single fixed vantage point. Metamoran enables rich long-range depth imaging outdoors with applications to roadside safety infrastructure, surveillance and wide-area mapping. Our key insight is to use the high azimuth resolution from cameras using computer vision techniques, including image segmentation and monocular depth estimation, to obtain object shapes and use these as priors for our novel specular beamforming algorithm. We also design this algorithm to work in cluttered environments with weak reflections and in partially occluded scenarios. We perform a detailed evaluation of Metamoran's depth imaging and sensing capabilities in 200 diverse scenes at a major U.S. city. Our evaluation shows that Metamoran estimates the depth of an object up to 60m away with a median error of 28cm, an improvement of 13$\times$ compared to a naive radar+camera baseline and 23$\times$ compared to monocular depth estimation.

36.G$^2$DA: Geometry-Guided Dual-Alignment Learning for RGB-Infrared Person Re-Identification ⬇️

RGB-Infrared (IR) person re-identification aims to retrieve person-of-interest between heterogeneous modalities, suffering from large modality discrepancy caused by different sensory devices. Existing methods mainly focus on global-level modality alignment, whereas neglect sample-level modality divergence to some extent, leading to performance degradation. This paper attempts to find RGB-IR ReID solutions from tackling sample-level modality difference, and presents a Geometry-Guided Dual-Alignment learning framework (G$^2$DA), which jointly enhances modality-invariance and reinforces discriminability with human topological structure in features to boost the overall matching performance. Specifically, G$^2$DA extracts accurate body part features with a pose estimator, serving as a semantic bridge complementing the missing local details in global descriptor. Based on extracted local and global features, a novel distribution constraint derived from optimal transport is introduced to mitigate the modality gap in a fine-grained sample-level manner. Beyond pair-wise relations across two modalities, it additionally measures the structural similarity of different parts, thus both multi-level features and their relations are kept consistent in the common feature space. Considering the inherent human-topology information, we further advance a geometry-guided graph learning module to refine each part features, where relevant regions can be emphasized while meaningless ones are suppressed, effectively facilitating robust feature learning. Extensive experiments on two standard benchmark datasets validate the superiority of our proposed method, yielding competitive performance over the state-of-the-art approaches.

37.Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collection ⬇️

Non-parametric face modeling aims to reconstruct 3D face only from images without shape assumptions. While plausible facial details are predicted, the models tend to over-depend on local color appearance and suffer from ambiguous noise. To address such problem, this paper presents a novel Learning to Aggregate and Personalize (LAP) framework for unsupervised robust 3D face modeling. Instead of using controlled environment, the proposed method implicitly disentangles ID-consistent and scene-specific face from unconstrained photo set. Specifically, to learn ID-consistent face, LAP adaptively aggregates intrinsic face factors of an identity based on a novel curriculum learning approach with relaxed consistency loss. To adapt the face for a personalized scene, we propose a novel attribute-refining network to modify ID-consistent face with target attribute and details. Based on the proposed method, we make unsupervised 3D face modeling benefit from meaningful image facial structure and possibly higher resolutions. Extensive experiments on benchmarks show LAP recovers superior or competitive face shape and texture, compared with state-of-the-art (SOTA) methods with or without prior and supervision.

38.Cluster-guided Asymmetric Contrastive Learning for Unsupervised Person Re-Identification ⬇️

Unsupervised person re-identification (Re-ID) aims to match pedestrian images from different camera views in unsupervised setting. Existing methods for unsupervised person Re-ID are usually built upon the pseudo labels from clustering. However, the quality of clustering depends heavily on the quality of the learned features, which are overwhelmingly dominated by the colors in images especially in the unsupervised setting. In this paper, we propose a Cluster-guided Asymmetric Contrastive Learning (CACL) approach for unsupervised person Re-ID, in which cluster structure is leveraged to guide the feature learning in a properly designed asymmetric contrastive learning framework. To be specific, we propose a novel cluster-level contrastive loss to help the siamese network effectively mine the invariance in feature learning with respect to the cluster structure within and between different data augmentation views, respectively. Extensive experiments conducted on three benchmark datasets demonstrate superior performance of our proposal.

39.Canonical Face Embeddings ⬇️

We present evidence that many common convolutional neural networks (CNNs) trained for face verification learn functions that are nearly equivalent under rotation. More specifically, we demonstrate that one face verification model's embeddings (i.e. last--layer activations) can be compared directly to another model's embeddings after only a rotation or linear transformation, with little performance penalty. This finding is demonstrated using IJB-C 1:1 verification across the combinations of ten modern off-the-shelf CNN-based face verification models which vary in training dataset, CNN architecture, way of using angular loss, or some combination of the 3, and achieve a mean true accept rate of 0.96 at a false accept rate of 0.01. When instead evaluating embeddings generated from two CNNs, where one CNN's embeddings are mapped with a linear transformation, the mean true accept rate drops to 0.95 using the same verification paradigm. Restricting these linear maps to only perform rotation produces a mean true accept rate of 0.91. These mappings' existence suggests that a common representation is learned by models with variation in training or structure. A discovery such as this likely has broad implications, and we provide an application in which face embeddings can be de-anonymized using a limited number of samples.

40.Efficient Facial Expression Analysis For Dimensional Affect Recognition Using Geometric Features ⬇️

Despite their continued popularity, categorical approaches to affect recognition have limitations, especially in real-life situations. Dimensional models of affect offer important advantages for the recognition of subtle expressions and more fine-grained analysis. We introduce a simple but effective facial expression analysis (FEA) system for dimensional affect, solely based on geometric features and Partial Least Squares (PLS) regression. The system jointly learns to estimate Arousal and Valence ratings from a set of facial images. The proposed approach is robust, efficient, and exhibits comparable performance to contemporary deep learning models, while requiring a fraction of the computational resources.

41.Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Data ⬇️

Most existing works in few-shot learning rely on meta-learning the network on a large base dataset which is typically from the same domain as the target dataset. We tackle the problem of cross-domain few-shot learning where there is a large shift between the base and target domain. The problem of cross-domain few-shot recognition with unlabeled target data is largely unaddressed in the literature. STARTUP was the first method that tackles this problem using self-training. However, it uses a fixed teacher pretrained on a labeled base dataset to create soft labels for the unlabeled target samples. As the base dataset and unlabeled dataset are from different domains, projecting the target images in the class-domain of the base dataset with a fixed pretrained model might be sub-optimal. We propose a simple dynamic distillation-based approach to facilitate unlabeled images from the novel/base dataset. We impose consistency regularization by calculating predictions from the weakly-augmented versions of the unlabeled images from a teacher network and matching it with the strongly augmented versions of the same images from a student network. The parameters of the teacher network are updated as exponential moving average of the parameters of the student network. We show that the proposed network learns representation that can be easily adapted to the target domain even though it has not been trained with target-specific classes during the pretraining phase. Our model outperforms the current state-of-the art method by 4.4% for 1-shot and 3.6% for 5-shot classification in the BSCD-FSL benchmark, and also shows competitive performance on traditional in-domain few-shot learning task. Our code will be available at: this https URL.

42.DFM: A Performance Baseline for Deep Feature Matching ⬇️

A novel image matching method is proposed that utilizes learned features extracted by an off-the-shelf deep neural network to obtain a promising performance. The proposed method uses pre-trained VGG architecture as a feature extractor and does not require any additional training specific to improve matching. Inspired by well-established concepts in the psychology area, such as the Mental Rotation paradigm, an initial warping is performed as a result of a preliminary geometric transformation estimate. These estimates are simply based on dense matching of nearest neighbors at the terminal layer of VGG network outputs of the images to be matched. After this initial alignment, the same approach is repeated again between reference and aligned images in a hierarchical manner to reach a good localization and matching performance. Our algorithm achieves 0.57 and 0.80 overall scores in terms of Mean Matching Accuracy (MMA) for 1 pixel and 2 pixels thresholds respectively on Hpatches dataset, which indicates a better performance than the state-of-the-art.

43.Flow Guided Transformable Bottleneck Networks for Motion Retargeting ⬇️

Human motion retargeting aims to transfer the motion of one person in a "driving" video or set of images to another person. Existing efforts leverage a long training video from each target person to train a subject-specific motion transfer model. However, the scalability of such methods is limited, as each model can only generate videos for the given target subject, and such training videos are labor-intensive to acquire and process. Few-shot motion transfer techniques, which only require one or a few images from a target, have recently drawn considerable attention. Methods addressing this task generally use either 2D or explicit 3D representations to transfer motion, and in doing so, sacrifice either accurate geometric modeling or the flexibility of an end-to-end learned representation. Inspired by the Transformable Bottleneck Network, which renders novel views and manipulations of rigid objects, we propose an approach based on an implicit volumetric representation of the image content, which can then be spatially manipulated using volumetric flow fields. We address the challenging question of how to aggregate information across different body poses, learning flow fields that allow for combining content from the appropriate regions of input images of highly non-rigid human subjects performing complex motions into a single implicit volumetric representation. This allows us to learn our 3D representation solely from videos of moving people. Armed with both 3D object understanding and end-to-end learned rendering, this categorically novel representation delivers state-of-the-art image generation quality, as shown by our quantitative and qualitative evaluations.

44.Potato Crop Stress Identification in Aerial Images using Deep Learning-based Object Detection ⬇️

Recent research on the application of remote sensing and deep learning-based analysis in precision agriculture demonstrated a potential for improved crop management and reduced environmental impacts of agricultural production. Despite the promising results, the practical relevance of these technologies for actual field deployment requires novel algorithms that are customized for analysis of agricultural images and robust to implementation on natural field imagery. The paper presents an approach for analyzing aerial images of a potato crop using deep neural networks. The main objective is to demonstrate automated spatial recognition of a healthy versus stressed crop at a plant level. Specifically, we examine premature plant senescence resulting in drought stress on Russet Burbank potato plants. The proposed deep learning model, named Retina-UNet-Ag, is a variant of Retina-UNet (Jaeger et al., 2018) and includes connections from low-level semantic dense representation maps to the feature pyramid network. The paper also introduces a dataset of field images acquired with a Parrot Sequoia camera carried by a Solo unmanned aerial vehicle. Experimental validation demonstrated the ability for distinguishing healthy and stressed plants in field images, achieving an average Dice score coefficient of 0.74. A comparison to related state-of-the-art deep learning models for object detection revealed that the presented approach is effective for the task at hand. The method applied here is conducive toward the assessment and recognition of potato crop stress (early plant senescence resulting from drought stress in this case) in natural aerial field images collected under real conditions.

45.Learning Deep Morphological Networks with Neural Architecture Search ⬇️

Deep Neural Networks (DNNs) are generated by sequentially performing linear and non-linear processes. Using a combination of linear and non-linear procedures is critical for generating a sufficiently deep feature space. The majority of non-linear operators are derivations of activation functions or pooling functions. Mathematical morphology is a branch of mathematics that provides non-linear operators for a variety of image processing problems. We investigate the utility of integrating these operations in an end-to-end deep learning framework in this paper. DNNs are designed to acquire a realistic representation for a particular job. Morphological operators give topological descriptors that convey salient information about the shapes of objects depicted in images. We propose a method based on meta-learning to incorporate morphological operators into DNNs. The learned architecture demonstrates how our novel morphological operations significantly increase DNN performance on various tasks, including picture classification and edge detection.

46.Face Age Progression With Attribute Manipulation ⬇️

Face is one of the predominant means of person recognition. In the process of ageing, human face is prone to many factors such as time, attributes, weather and other subject specific variations. The impact of these factors were not well studied in the literature of face aging. In this paper, we propose a novel holistic model in this regard viz., ``Face Age progression With Attribute Manipulation (FAWAM)", i.e. generating face images at different ages while simultaneously varying attributes and other subject specific characteristics. We address the task in a bottom-up manner, as two submodules i.e. face age progression and face attribute manipulation. For face aging, we use an attribute-conscious face aging model with a pyramidal generative adversarial network that can model age-specific facial changes while maintaining intrinsic subject specific characteristics. For facial attribute manipulation, the age processed facial image is manipulated with desired attributes while preserving other details unchanged, leveraging an attribute generative adversarial network architecture. We conduct extensive analysis in standard large scale datasets and our model achieves significant performance both quantitatively and qualitatively.

47.Self-Supervised Learning with Kernel Dependence Maximization ⬇️

We approach self-supervised learning of image representations from a statistical dependence perspective, proposing Self-Supervised Learning with the Hilbert-Schmidt Independence Criterion (SSL-HSIC). SSL-HSIC maximizes dependence between representations of transformed versions of an image and the image identity, while minimizing the kernelized variance of those features. This self-supervised learning framework yields a new understanding of InfoNCE, a variational lower bound on the mutual information (MI) between different transformations. While the MI itself is known to have pathologies which can result in meaningless representations being learned, its bound is much better behaved: we show that it implicitly approximates SSL-HSIC (with a slightly different regularizer). Our approach also gives us insight into BYOL, since SSL-HSIC similarly learns local neighborhoods of samples. SSL-HSIC allows us to directly optimize statistical dependence in time linear in the batch size, without restrictive data assumptions or indirect mutual information estimators. Trained with or without a target network, SSL-HSIC matches the current state-of-the-art for standard linear evaluation on ImageNet, semi-supervised learning and transfer to other classification and vision tasks such as semantic segmentation, depth estimation and object recognition.

48.Efficient Micro-Structured Weight Unification for Neural Network Compression ⬇️

Compressing Deep Neural Network (DNN) models to alleviate the storage and computation requirements is essential for practical applications, especially for resource limited devices. Although capable of reducing a reasonable amount of model parameters, previous unstructured or structured weight pruning methods can hardly truly accelerate inference, either due to the poor hardware compatibility of the unstructured sparsity or due to the low sparse rate of the structurally pruned network. Aiming at reducing both storage and computation, as well as preserving the original task performance, we propose a generalized weight unification framework at a hardware compatible micro-structured level to achieve high amount of compression and acceleration. Weight coefficients of a selected micro-structured block are unified to reduce the storage and computation of the block without changing the neuron connections, which turns to a micro-structured pruning special case when all unified coefficients are set to zero, where neuron connections (hence storage and computation) are completely removed. In addition, we developed an effective training framework based on the alternating direction method of multipliers (ADMM), which converts our complex constrained optimization into separately solvable subproblems. Through iteratively optimizing the subproblems, the desired micro-structure can be ensured with high compression ratio and low performance degradation. We extensively evaluated our method using a variety of benchmark models and datasets for different applications. Experimental results demonstrate state-of-the-art performance.

49.A White Paper on Neural Network Quantization ⬇️

While neural networks have advanced the frontiers in many applications, they often come at a high computational cost. Reducing the power and latency of neural network inference is key if we want to integrate modern networks into edge devices with strict power and compute requirements. Neural network quantization is one of the most effective ways of achieving these savings but the additional noise it induces can lead to accuracy degradation. In this white paper, we introduce state-of-the-art algorithms for mitigating the impact of quantization noise on the network's performance while maintaining low-bit weights and activations. We start with a hardware motivated introduction to quantization and then consider two main classes of algorithms: Post-Training Quantization (PTQ) and Quantization-Aware-Training (QAT). PTQ requires no re-training or labelled data and is thus a lightweight push-button approach to quantization. In most cases, PTQ is sufficient for achieving 8-bit quantization with close to floating-point accuracy. QAT requires fine-tuning and access to labeled training data but enables lower bit quantization with competitive results. For both solutions, we provide tested pipelines based on existing literature and extensive experimentation that lead to state-of-the-art performance for common deep learning models and tasks.

50.Physion: Evaluating Physical Prediction from Vision in Humans and Machines ⬇️

While machine learning algorithms excel at many challenging visual tasks, it is unclear that they can make predictions about commonplace real world physical events. Here, we present a visual and physical prediction benchmark that precisely measures this capability. In realistically simulating a wide variety of physical phenomena -- rigid and soft-body collisions, stable multi-object configurations, rolling and sliding, projectile motion -- our dataset presents a more comprehensive challenge than existing benchmarks. Moreover, we have collected human responses for our stimuli so that model predictions can be directly compared to human judgments. We compare an array of algorithms -- varying in their architecture, learning objective, input-output structure, and training data -- on their ability to make diverse physical predictions. We find that graph neural networks with access to the physical state best capture human behavior, whereas among models that receive only visual input, those with object-centric representations or pretraining do best but fall far short of human accuracy. This suggests that extracting physically meaningful representations of scenes is the main bottleneck to achieving human-like visual prediction. We thus demonstrate how our benchmark can identify areas for improvement and measure progress on this key aspect of physical understanding.

51.SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients ⬇️

Adaptive gradient methods have shown excellent performance for solving many machine learning problems. Although multiple adaptive methods were recently studied, they mainly focus on either empirical or theoretical aspects and also only work for specific problems by using specific adaptive learning rates. It is desired to design a universal framework for practical algorithms of adaptive gradients with theoretical guarantee to solve general problems. To fill this gap, we propose a faster and universal framework of adaptive gradients (i.e., SUPER-ADAM) by introducing a universal adaptive matrix that includes most existing adaptive gradient forms. Moreover, our framework can flexibly integrates the momentum and variance reduced techniques. In particular, our novel framework provides the convergence analysis support for adaptive gradient methods under the nonconvex setting. In theoretical analysis, we prove that our new algorithm can achieve the best known complexity of $\tilde{O}(\epsilon^{-3})$ for finding an $\epsilon$-stationary point of nonconvex optimization, which matches the lower bound for stochastic smooth nonconvex optimization. In numerical experiments, we employ various deep learning tasks to validate that our algorithm consistently outperforms the existing adaptive algorithms.

52.Optimal Latent Vector Alignment for Unsupervised Domain Adaptation in Medical Image Segmentation ⬇️

This paper addresses the domain shift problem for segmentation. As a solution, we propose OLVA, a novel and lightweight unsupervised domain adaptation method based on a Variational Auto-Encoder (VAE) and Optimal Transport (OT) theory. Thanks to the VAE, our model learns a shared cross-domain latent space that follows a normal distribution, which reduces the domain shift. To guarantee valid segmentations, our shared latent space is designed to model the shape rather than the intensity variations. We further rely on an OT loss to match and align the remaining discrepancy between the two domains in the latent space. We demonstrate OLVA's effectiveness for the segmentation of multiple cardiac structures on the public Multi-Modality Whole Heart Segmentation (MM-WHS) dataset, where the source domain consists of annotated 3D MR images and the unlabelled target domain of 3D CTs. Our results show remarkable improvements with an additional margin of 12.5% dice score over concurrent generative training approaches.

53.Automated triaging of head MRI examinations using convolutional neural networks ⬇️

The growing demand for head magnetic resonance imaging (MRI) examinations, along with a global shortage of radiologists, has led to an increase in the time taken to report head MRI scans around the world. For many neurological conditions, this delay can result in increased morbidity and mortality. An automated triaging tool could reduce reporting times for abnormal examinations by identifying abnormalities at the time of imaging and prioritizing the reporting of these scans. In this work, we present a convolutional neural network for detecting clinically-relevant abnormalities in $\text{T}_2$-weighted head MRI scans. Using a validated neuroradiology report classifier, we generated a labelled dataset of 43,754 scans from two large UK hospitals for model training, and demonstrate accurate classification (area under the receiver operating curve (AUC) = 0.943) on a test set of 800 scans labelled by a team of neuroradiologists. Importantly, when trained on scans from only a single hospital the model generalized to scans from the other hospital ($\Delta$AUC $\leq$ 0.02). A simulation study demonstrated that our model would reduce the mean reporting time for abnormal examinations from 28 days to 14 days and from 9 days to 5 days at the two hospitals, demonstrating feasibility for use in a clinical triage environment.

54.Automatic linear measurements of the fetal brain on MRI with deep neural networks ⬇️

Timely, accurate and reliable assessment of fetal brain development is essential to reduce short and long-term risks to fetus and mother. Fetal MRI is increasingly used for fetal brain assessment. Three key biometric linear measurements important for fetal brain evaluation are Cerebral Biparietal Diameter (CBD), Bone Biparietal Diameter (BBD), and Trans-Cerebellum Diameter (TCD), obtained manually by expert radiologists on reference slices, which is time consuming and prone to human error. The aim of this study was to develop a fully automatic method computing the CBD, BBD and TCD measurements from fetal brain MRI. The input is fetal brain MRI volumes which may include the fetal body and the mother's abdomen. The outputs are the measurement values and reference slices on which the measurements were computed. The method, which follows the manual measurements principle, consists of five stages: 1) computation of a Region Of Interest that includes the fetal brain with an anisotropic 3D U-Net classifier; 2) reference slice selection with a Convolutional Neural Network; 3) slice-wise fetal brain structures segmentation with a multiclass U-Net classifier; 4) computation of the fetal brain midsagittal line and fetal brain orientation, and; 5) computation of the measurements. Experimental results on 214 volumes for CBD, BBD and TCD measurements yielded a mean $L_1$ difference of 1.55mm, 1.45mm and 1.23mm respectively, and a Bland-Altman 95% confidence interval ($CI_{95}$) of 3.92mm, 3.98mm and 2.25mm respectively. These results are similar to the manual inter-observer variability. The proposed automatic method for computing biometric linear measurements of the fetal brain from MR imaging achieves human level performance. It has the potential of being a useful method for the assessment of fetal brain biometry in normal and pathological cases, and of improving routine clinical practice.

55.How Modular Should Neural Module Networks Be for Systematic Generalization? ⬇️

Neural Module Networks (NMNs) aim at Visual Question Answering (VQA) via composition of modules that tackle a sub-task. NMNs are a promising strategy to achieve systematic generalization, i.e. overcoming biasing factors in the training distribution. However, the aspects of NMNs that facilitate systematic generalization are not fully understood. In this paper, we demonstrate that the stage and the degree at which modularity is defined has large influence on systematic generalization. In a series of experiments on three VQA datasets (MNIST with multiple attributes, SQOOP, and CLEVR-CoGenT), our results reveal that tuning the degree of modularity in the network, especially at the image encoder stage, reaches substantially higher systematic generalization. These findings lead to new NMN architectures that outperform previous ones in terms of systematic generalization.

56.EuroCrops: A Pan-European Dataset for Time Series Crop Type Classification ⬇️

We present EuroCrops, a dataset based on self-declared field annotations for training and evaluating methods for crop type classification and mapping, together with its process of acquisition and harmonisation. By this, we aim to enrich the research efforts and discussion for data-driven land cover classification via Earth observation and remote sensing. Additionally, through inclusion of self-declarations gathered in the scope of subsidy control from all countries of the European Union (EU), this dataset highlights the difficulties and pitfalls one comes across when operating on a transnational level. We, therefore, also introduce a new taxonomy scheme, HCAT-ID, that aspires to capture all the aspects of reference data originating from administrative and agency databases. To address researchers from both the remote sensing and the computer vision and machine learning communities, we publish the dataset in different formats and processing levels.

57.Perceptually-inspired super-resolution of compressed videos ⬇️

Spatial resolution adaptation is a technique which has often been employed in video compression to enhance coding efficiency. This approach encodes a lower resolution version of the input video and reconstructs the original resolution during decoding. Instead of using conventional up-sampling filters, recent work has employed advanced super-resolution methods based on convolutional neural networks (CNNs) to further improve reconstruction quality. These approaches are usually trained to minimise pixel-based losses such as Mean-Squared Error (MSE), despite the fact that this type of loss metric does not correlate well with subjective opinions. In this paper, a perceptually-inspired super-resolution approach (M-SRGAN) is proposed for spatial up-sampling of compressed video using a modified CNN model, which has been trained using a generative adversarial network (GAN) on compressed content with perceptual loss functions. The proposed method was integrated with HEVC HM 16.20, and has been evaluated on the JVET Common Test Conditions (UHD test sequences) using the Random Access configuration. The results show evident perceptual quality improvement over the original HM 16.20, with an average bitrate saving of 35.6% (Bjøntegaard Delta measurement) based on a perceptual quality metric, VMAF.

58.Contextualizing Multiple Tasks via Learning to Decompose ⬇️

One single instance could possess multiple portraits and reveal diverse relationships with others according to different contexts. Those ambiguities increase the difficulty of learning a generalizable model when there exists one concept or mixed concepts in a task. We propose a general approach Learning to Decompose Network (LeadNet) for both two cases, which contextualizes a model through meta-learning multiple maps for concepts discovery -- the representations of instances are decomposed and adapted conditioned on the contexts. Through taking a holistic view over multiple latent components over instances in a sampled pseudo task, LeadNet learns to automatically select the right concept via incorporating those rich semantics inside and between objects. LeadNet demonstrates its superiority in various applications, including exploring multiple views of confusing tasks, out-of-distribution recognition, and few-shot image classification.

59.ResDepth: A Deep Prior For 3D Reconstruction From High-resolution Satellite Images ⬇️

Modern optical satellite sensors enable high-resolution stereo reconstruction from space. But the challenging imaging conditions when observing the Earth from space push stereo matching to its limits. In practice, the resulting digital surface models (DSMs) are fairly noisy and often do not attain the accuracy needed for high-resolution applications such as 3D city modeling. Arguably, stereo correspondence based on low-level image similarity is insufficient and should be complemented with a-priori knowledge about the expected surface geometry beyond basic local smoothness. To that end, we introduce ResDepth, a convolutional neural network that learns such an expressive geometric prior from example data. ResDepth refines an initial, raw stereo DSM while conditioning the refinement on the images. I.e., it acts as a smart, learned post-processing filter and can seamlessly complement any stereo matching pipeline. In a series of experiments, we find that the proposed method consistently improves stereo DSMs both quantitatively and qualitatively. We show that the prior encoded in the network weights captures meaningful geometric characteristics of urban design, which also generalize across different districts and even from one city to another. Moreover, we demonstrate that, by training on a variety of stereo pairs, ResDepth can acquire a sufficient degree of invariance against variations in imaging conditions and acquisition geometry.

60.Cine-MRI detection of abdominal adhesions with spatio-temporal deep learning ⬇️

Adhesions are an important cause of chronic pain following abdominal surgery. Recent developments in abdominal cine-MRI have enabled the non-invasive diagnosis of adhesions. Adhesions are identified on cine-MRI by the absence of sliding motion during movement. Diagnosis and mapping of adhesions improves the management of patients with pain. Detection of abdominal adhesions on cine-MRI is challenging from both a radiological and deep learning perspective. We focus on classifying presence or absence of adhesions in sagittal abdominal cine-MRI series. We experimented with spatio-temporal deep learning architectures centered around a ConvGRU architecture. A hybrid architecture comprising a ResNet followed by a ConvGRU model allows to classify a whole time-series. Compared to a stand-alone ResNet with a two time-point (inspiration/expiration) input, we show an increase in classification performance (AUROC) from 0.74 to 0.83 ($p<0.05$). Our full temporal classification approach adds only a small amount (5%) of parameters to the entire architecture, which may be useful for other medical imaging problems with a temporal dimension.

61.Mean Embeddings with Test-Time Data Augmentation for Ensembling of Representations ⬇️

Averaging predictions over a set of models -- an ensemble -- is widely used to improve predictive performance and uncertainty estimation of deep learning models. At the same time, many machine learning systems, such as search, matching, and recommendation systems, heavily rely on embeddings. Unfortunately, due to misalignment of features of independently trained models, embeddings, cannot be improved with a naive deep ensemble like approach. In this work, we look at the ensembling of representations and propose mean embeddings with test-time augmentation (MeTTA) simple yet well-performing recipe for ensembling representations. Empirically we demonstrate that MeTTA significantly boosts the quality of linear evaluation on ImageNet for both supervised and self-supervised models. Even more exciting, we draw connections between MeTTA, image retrieval, and transformation invariant models. We believe that spreading the success of ensembles to inference higher-quality representations is the important step that will open many new applications of ensembling.

62.Revisiting the Calibration of Modern Neural Networks ⬇️

Accurate estimation of predictive uncertainty (model calibration) is essential for the safe application of neural networks. Many instances of miscalibration in modern neural networks have been reported, suggesting a trend that newer, more accurate models produce poorly calibrated predictions. Here, we revisit this question for recent state-of-the-art image classification models. We systematically relate model calibration and accuracy, and find that the most recent models, notably those not using convolutions, are among the best calibrated. Trends observed in prior model generations, such as decay of calibration with distribution shift or model size, are less pronounced in recent architectures. We also show that model size and amount of pretraining do not fully explain these differences, suggesting that architecture is a major determinant of calibration properties.

63.End-to-End Learning of Keypoint Representations for Continuous Control from Images ⬇️

In many control problems that include vision, optimal controls can be inferred from the location of the objects in the scene. This information can be represented using keypoints, which is a list of spatial locations in the input image. Previous works show that keypoint representations learned during unsupervised pre-training using encoder-decoder architectures can provide good features for control tasks. In this paper, we show that it is possible to learn efficient keypoint representations end-to-end, without the need for unsupervised pre-training, decoders, or additional losses. Our proposed architecture consists of a differentiable keypoint extractor that feeds the coordinates of the estimated keypoints directly to a soft actor-critic agent. The proposed algorithm yields performance competitive to the state-of-the art on DeepMind Control Suite tasks.

64.A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization ⬇️

Bi-level optimization model is able to capture a wide range of complex learning tasks with practical interest. Due to the witnessed efficiency in solving bi-level programs, gradient-based methods have gained popularity in the machine learning community. In this work, we propose a new gradient-based solution scheme, namely, the Bi-level Value-Function-based Interior-point Method (BVFIM). Following the main idea of the log-barrier interior-point scheme, we penalize the regularized value function of the lower level problem into the upper level objective. By further solving a sequence of differentiable unconstrained approximation problems, we consequently derive a sequential programming scheme. The numerical advantage of our scheme relies on the fact that, when gradient methods are applied to solve the approximation problem, we successfully avoid computing any expensive Hessian-vector or Jacobian-vector product. We prove the convergence without requiring any convexity assumption on either the upper level or the lower level objective. Experiments demonstrate the efficiency of the proposed BVFIM on non-convex bi-level problems.

65.Wavelength-based Attributed Deep Neural Network for Underwater Image Restoration ⬇️

Underwater images, in general, suffer from low contrast and high color distortions due to the non-uniform attenuation of the light as it propagates through the water. In addition, the degree of attenuation varies with the wavelength resulting in the asymmetric traversing of colors. Despite the prolific works for underwater image restoration (UIR) using deep learning, the above asymmetricity has not been addressed in the respective network engineering. As the first novelty, this paper shows that attributing the right receptive field size (context) based on the traversing range of the color channel may lead to a substantial performance gain for the task of UIR. Further, it is important to suppress the irrelevant multi-contextual features and increase the representational power of the model. Therefore, as a second novelty, we have incorporated an attentive skip mechanism to adaptively refine the learned multi-contextual features. The proposed framework, called Deep WaveNet, is optimized using the traditional pixel-wise and feature-based cost functions. An extensive set of experiments have been carried out to show the efficacy of the proposed scheme over existing best-published literature on benchmark datasets. More importantly, we have demonstrated a comprehensive validation of enhanced images across various high-level vision tasks, e.g., underwater image semantic segmentation, and diver's 2D pose estimation. A sample video to exhibit our real-world performance is available at \url{this https URL}.

66.Non-Gradient Manifold Neural Network ⬇️

Deep neural network (DNN) generally takes thousands of iterations to optimize via gradient descent and thus has a slow convergence. In addition, softmax, as a decision layer, may ignore the distribution information of the data during classification. Aiming to tackle the referred problems, we propose a novel manifold neural network based on non-gradient optimization, i.e., the closed-form solutions. Considering that the activation function is generally invertible, we reconstruct the network via forward ridge regression and low rank backward approximation, which achieve the rapid convergence. Moreover, by unifying the flexible Stiefel manifold and adaptive support vector machine, we devise the novel decision layer which efficiently fits the manifold structure of the data and label information. Consequently, a jointly non-gradient optimization method is designed to generate the network with closed-form results. Eventually, extensive experiments validate the superior performance of the model.

67.Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models ⬇️

Out-of-distribution (OOD) detection is an important task in machine learning systems for ensuring their reliability and safety. Deep probabilistic generative models facilitate OOD detection by estimating the likelihood of a data sample. However, such models frequently assign a suspiciously high likelihood to a specific outlier. Several recent works have addressed this issue by training a neural network with auxiliary outliers, which are generated by perturbing the input data. In this paper, we discover that these approaches fail for certain OOD datasets. Thus, we suggest a new detection metric that operates without outlier exposure. We observe that our metric is robust to diverse variations of an image compared to the previous outlier-exposing methods. Furthermore, our proposed score requires neither auxiliary models nor additional training. Instead, this paper utilizes the likelihood ratio statistic in a new perspective to extract genuine properties from the given single deep probabilistic generative model. We also apply a novel numerical approximation to enable fast implementation. Finally, we demonstrate comprehensive experiments on various probabilistic generative models and show that our method achieves state-of-the-art performance.

68.Scaling Neural Tangent Kernels via Sketching and Random Features ⬇️

The Neural Tangent Kernel (NTK) characterizes the behavior of infinitely-wide neural networks trained under least squares loss by gradient descent. Recent works also report that NTK regression can outperform finitely-wide neural networks trained on small-scale datasets. However, the computational complexity of kernel methods has limited its use in large-scale learning tasks. To accelerate learning with NTK, we design a near input-sparsity time approximation algorithm for NTK, by sketching the polynomial expansions of arc-cosine kernels: our sketch for the convolutional counterpart of NTK (CNTK) can transform any image using a linear runtime in the number of pixels. Furthermore, we prove a spectral approximation guarantee for the NTK matrix, by combining random features (based on leverage score sampling) of the arc-cosine kernels with a sketching algorithm. We benchmark our methods on various large-scale regression and classification tasks and show that a linear regressor trained on our CNTK features matches the accuracy of exact CNTK on CIFAR-10 dataset while achieving 150x speedup.

69.A Lightweight ReLU-Based Feature Fusion for Aerial Scene Classification ⬇️

In this paper, we propose a transfer-learning based model construction technique for the aerial scene classification problem. The core of our technique is a layer selection strategy, named ReLU-Based Feature Fusion (RBFF), that extracts feature maps from a pretrained CNN-based single-object image classification model, namely MobileNetV2, and constructs a model for the aerial scene classification task. RBFF stacks features extracted from the batch normalization layer of a few selected blocks of MobileNetV2, where the candidate blocks are selected based on the characteristics of the ReLU activation layers present in those blocks. The feature vector is then compressed into a low-dimensional feature space using dimension reduction algorithms on which we train a low-cost SVM classifier for the classification of the aerial images. We validate our choice of selected features based on the significance of the extracted features with respect to our classification pipeline. RBFF remarkably does not involve any training of the base CNN model except for a few parameters for the classifier, which makes the technique very cost-effective for practical deployments. The constructed model despite being lightweight outperforms several recently proposed models in terms of accuracy for a number of aerial scene datasets.

70.Defending Touch-based Continuous Authentication Systems from Active Adversaries Using Generative Adversarial Networks ⬇️

Previous studies have demonstrated that commonly studied (vanilla) touch-based continuous authentication systems (V-TCAS) are susceptible to population attack. This paper proposes a novel Generative Adversarial Network assisted TCAS (G-TCAS) framework, which showed more resilience to the population attack. G-TCAS framework was tested on a dataset of 117 users who interacted with a smartphone and tablet pair. On average, the increase in the false accept rates (FARs) for V-TCAS was much higher (22%) than G-TCAS (13%) for the smartphone. Likewise, the increase in the FARs for V-TCAS was 25% compared to G-TCAS (6%) for the tablet.

71.Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge Distillation ⬇️

In recent years the ubiquitous deployment of AI has posed great concerns in regards to algorithmic bias, discrimination, and fairness. Compared to traditional forms of bias or discrimination caused by humans, algorithmic bias generated by AI is more abstract and unintuitive therefore more difficult to explain and mitigate. A clear gap exists in the current literature on evaluating and mitigating bias in pruned neural networks. In this work, we strive to tackle the challenging issues of evaluating, mitigating, and explaining induced bias in pruned neural networks. Our paper makes three contributions. First, we propose two simple yet effective metrics, Combined Error Variance (CEV) and Symmetric Distance Error (SDE), to quantitatively evaluate the induced bias prevention quality of pruned models. Second, we demonstrate that knowledge distillation can mitigate induced bias in pruned neural networks, even with unbalanced datasets. Third, we reveal that model similarity has strong correlations with pruning induced bias, which provides a powerful method to explain why bias occurs in pruned neural networks. Our code is available at this https URL

72.Learning Stable Classifiers by Transferring Unstable Features ⬇️

We study transfer learning in the presence of spurious correlations. We experimentally demonstrate that directly transferring the stable feature extractor learned on the source task may not eliminate these biases for the target task. However, we hypothesize that the unstable features in the source task and those in the target task are directly related. By explicitly informing the target classifier of the source task's unstable features, we can regularize the biases in the target task. Specifically, we derive a representation that encodes the unstable features by contrasting different data environments in the source task. On the target task, we cluster data from this representation, and achieve robustness by minimizing the worst-case risk across all clusters. We evaluate our method on both text and image classifications. Empirical results demonstrate that our algorithm is able to maintain robustness on the target task, outperforming the best baseline by 22.9% in absolute accuracy across 12 transfer settings. Our code is available at this https URL.

73.Temporal Consistency Checks to Detect LiDAR Spoofing Attacks on Autonomous Vehicle Perception ⬇️

LiDAR sensors are used widely in Autonomous Vehicles for better perceiving the environment which enables safer driving decisions. Recent work has demonstrated serious LiDAR spoofing attacks with alarming consequences. In particular, model-level LiDAR spoofing attacks aim to inject fake depth measurements to elicit ghost objects that are erroneously detected by 3D Object Detectors, resulting in hazardous driving decisions. In this work, we explore the use of motion as a physical invariant of genuine objects for detecting such attacks. Based on this, we propose a general methodology, 3D Temporal Consistency Check (3D-TC2), which leverages spatio-temporal information from motion prediction to verify objects detected by 3D Object Detectors. Our preliminary design and implementation of a 3D-TC2 prototype demonstrates very promising performance, providing more than 98% attack detection rate with a recall of 91% for detecting spoofed Vehicle (Car) objects, and is able to achieve real-time detection at 41Hz

74.Highdicom: A Python library for standardized encoding of image annotations and machine learning model outputs in pathology and radiology ⬇️

Machine learning is revolutionizing image-based diagnostics in pathology and radiology. ML models have shown promising results in research settings, but their lack of interoperability has been a major barrier for clinical integration and evaluation. The DICOM a standard specifies Information Object Definitions and Services for the representation and communication of digital images and related information, including image-derived annotations and analysis results. However, the complexity of the standard represents an obstacle for its adoption in the ML community and creates a need for software libraries and tools that simplify working with data sets in DICOM format. Here we present the highdicom library, which provides a high-level application programming interface for the Python programming language that abstracts low-level details of the standard and enables encoding and decoding of image-derived information in DICOM format in a few lines of Python code. The highdicom library ties into the extensive Python ecosystem for image processing and machine learning. Simultaneously, by simplifying creation and parsing of DICOM-compliant files, highdicom achieves interoperability with the medical imaging systems that hold the data used to train and run ML models, and ultimately communicate and store model outputs for clinical use. We demonstrate through experiments with slide microscopy and computed tomography imaging, that, by bridging these two ecosystems, highdicom enables developers to train and evaluate state-of-the-art ML models in pathology and radiology while remaining compliant with the DICOM standard and interoperable with clinical systems at all stages. To promote standardization of ML research and streamline the ML model development and deployment process, we made the library available free and open-source.

75.Learning Audio-Visual Dereverberation ⬇️

Reverberation from audio reflecting off surfaces and objects in the environment not only degrades the quality of speech for human perception, but also severely impacts the accuracy of automatic speech recognition. Prior work attempts to remove reverberation based on the audio modality only. Our idea is to learn to dereverberate speech from audio-visual observations. The visual environment surrounding a human speaker reveals important cues about the room geometry, materials, and speaker location, all of which influence the precise reverberation effects in the audio stream. We introduce Visually-Informed Dereverberation of Audio (VIDA), an end-to-end approach that learns to remove reverberation based on both the observed sounds and visual scene. In support of this new task, we develop a large-scale dataset that uses realistic acoustic renderings of speech in real-world 3D scans of homes offering a variety of room acoustics. Demonstrating our approach on both simulated and real imagery for speech enhancement, speech recognition, and speaker identification, we show it achieves state-of-the-art performance and substantially improves over traditional audio-only methods. Project page: this http URL.

76.CathAI: Fully Automated Interpretation of Coronary Angiograms Using Neural Networks ⬇️

Coronary heart disease (CHD) is the leading cause of adult death in the United States and worldwide, and for which the coronary angiography procedure is the primary gateway for diagnosis and clinical management decisions. The standard-of-care for interpretation of coronary angiograms depends upon ad-hoc visual assessment by the physician operator. However, ad-hoc visual interpretation of angiograms is poorly reproducible, highly variable and bias prone. Here we show for the first time that fully-automated angiogram interpretation to estimate coronary artery stenosis is possible using a sequence of deep neural network algorithms. The algorithmic pipeline we developed--called CathAI--achieves state-of-the art performance across the sequence of tasks required to accomplish automated interpretation of unselected, real-world angiograms. CathAI (Algorithms 1-2) demonstrated positive predictive value, sensitivity and F1 score of >=90% to identify the projection angle overall and >=93% for left or right coronary artery angiogram detection, the primary anatomic structures of interest. To predict obstructive coronary artery stenosis (>=70% stenosis), CathAI (Algorithm 4) exhibited an area under the receiver operating characteristic curve (AUC) of 0.862 (95% CI: 0.843-0.880). When externally validated in a healthcare system in another country, CathAI AUC was 0.869 (95% CI: 0.830-0.907) to predict obstructive coronary artery stenosis. Our results demonstrate that multiple purpose-built neural networks can function in sequence to accomplish the complex series of tasks required for automated analysis of real-world angiograms. Deployment of CathAI may serve to increase standardization and reproducibility in coronary stenosis assessment, while providing a robust foundation to accomplish future tasks for algorithmic angiographic interpretation.