1.Gradient-Based Interpretability Methods and Binarized Neural Networks ⬇️
Binarized Neural Networks (BNNs) have the potential to revolutionize the way that deep learning is carried out in edge computing platforms. However, the effectiveness of interpretability methods on these networks has not been assessed.
In this paper, we compare the performance of several widely used saliency map-based interpretabilty techniques (Gradient, SmoothGrad and GradCAM), when applied to Binarized or Full Precision Neural Networks (FPNNs). We found that the basic Gradient method produces very similar-looking maps for both types of network. However, SmoothGrad produces significantly noisier maps for BNNs. GradCAM also produces saliency maps which differ between network types, with some of the BNNs having seemingly nonsensical explanations. We comment on possible reasons for these differences in explanations and present it as an example of why interpretability techniques should be tested on a wider range of network types.
2.Multi-Class Classification of Blood Cells -- End to End Computer Vision based diagnosis case study ⬇️
The diagnosis of blood-based diseases often involves identifying and characterizing patient blood samples. Automated methods to detect and classify blood cell subtypes have important medical applications. Automated medical image processing and analysis offers a powerful tool for medical diagnosis. In this work we tackle the problem of white blood cell classification based on the morphological characteristics of their outer contour, color. The work we would explore a set of preprocessing and segmentation (Color-based segmentation, Morphological processing, contouring) algorithms along with a set of features extraction methods (Corner detection algorithms and Histogram of Gradients(HOG)), dimensionality reduction algorithms (Principal Component Analysis(PCA)) that are able to recognize and classify through various Unsupervised(k-nearest neighbors) and Supervised (Support Vector Machine, Decision Trees, Linear Discriminant Analysis, Quadratic Discriminant Analysis, Naive Bayes) algorithms different categories of white blood cells to Eosinophil, Lymphocyte, Monocyte, and Neutrophil. We even take a step forwards to explore various Deep Convolutional Neural network architecture (Sqeezent, MobilenetV1,MobilenetV2, InceptionNet etc.) without preprocessing/segmentation and with preprocessing. We would like to explore many algorithms to identify the robust algorithm with least time complexity and low resource requirement. The outcome of this work can be a cue to selection of algorithms as per requirement for automated blood cell classification.
3.Generative Self-training for Cross-domain Unsupervised Tagged-to-Cine MRI Synthesis ⬇️
Self-training based unsupervised domain adaptation (UDA) has shown great potential to address the problem of domain shift, when applying a trained deep learning model in a source domain to unlabeled target domains. However, while the self-training UDA has demonstrated its effectiveness on discriminative tasks, such as classification and segmentation, via the reliable pseudo-label selection based on the softmax discrete histogram, the self-training UDA for generative tasks, such as image synthesis, is not fully investigated. In this work, we propose a novel generative self-training (GST) UDA framework with continuous value prediction and regression objective for cross-domain image synthesis. Specifically, we propose to filter the pseudo-label with an uncertainty mask, and quantify the predictive confidence of generated images with practical variational Bayes learning. The fast test-time adaptation is achieved by a round-based alternative optimization scheme. We validated our framework on the tagged-to-cine magnetic resonance imaging (MRI) synthesis problem, where datasets in the source and target domains were acquired from different scanners or centers. Extensive validations were carried out to verify our framework against popular adversarial training UDA methods. Results show that our GST, with tagged MRI of test subjects in new target domains, improved the synthesis quality by a large margin, compared with the adversarial training UDA methods.
4.Adapting Off-the-Shelf Source Segmenter for Target Medical Image Segmentation ⬇️
Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a labeled source domain to an unlabeled and unseen target domain, which is usually trained on data from both domains. Access to the source domain data at the adaptation stage, however, is often limited, due to data storage or privacy issues. To alleviate this, in this work, we target source free UDA for segmentation, and propose to adapt an ``off-the-shelf" segmentation model pre-trained in the source domain to the target domain, with an adaptive batch-wise normalization statistics adaptation framework. Specifically, the domain-specific low-order batch statistics, i.e., mean and variance, are gradually adapted with an exponential momentum decay scheme, while the consistency of domain shareable high-order batch statistics, i.e., scaling and shifting parameters, is explicitly enforced by our optimization objective. The transferability of each channel is adaptively measured first from which to balance the contribution of each channel. Moreover, the proposed source free UDA framework is orthogonal to unsupervised learning methods, e.g., self-entropy minimization, which can thus be simply added on top of our framework. Extensive experiments on the BraTS 2018 database show that our source free UDA framework outperformed existing source-relaxed UDA methods for the cross-subtype UDA segmentation task and yielded comparable results for the cross-modality UDA segmentation task, compared with a supervised UDA methods with the source data.
5.A Circular-Structured Representation for Visual Emotion Distribution Learning ⬇️
Visual Emotion Analysis (VEA) has attracted increasing attention recently with the prevalence of sharing images on social networks. Since human emotions are ambiguous and subjective, it is more reasonable to address VEA in a label distribution learning (LDL) paradigm rather than a single-label classification task. Different from other LDL tasks, there exist intrinsic relationships between emotions and unique characteristics within them, as demonstrated in psychological theories. Inspired by this, we propose a well-grounded circular-structured representation to utilize the prior knowledge for visual emotion distribution learning. To be specific, we first construct an Emotion Circle to unify any emotional state within it. On the proposed Emotion Circle, each emotion distribution is represented with an emotion vector, which is defined with three attributes (i.e., emotion polarity, emotion type, emotion intensity) as well as two properties (i.e., similarity, additivity). Besides, we design a novel Progressive Circular (PC) loss to penalize the dissimilarities between predicted emotion vector and labeled one in a coarse-to-fine manner, which further boosts the learning process in an emotion-specific way. Extensive experiments and comparisons are conducted on public visual emotion distribution datasets, and the results demonstrate that the proposed method outperforms the state-of-the-art methods.
6.FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detection ⬇️
Accurate detection of obstacles in 3D is an essential task for autonomous driving and intelligent transportation. In this work, we propose a general multimodal fusion framework FusionPainting to fuse the 2D RGB image and 3D point clouds at a semantic level for boosting the 3D object detection task. Especially, the FusionPainting framework consists of three main modules: a multi-modal semantic segmentation module, an adaptive attention-based semantic fusion module, and a 3D object detector. First, semantic information is obtained for 2D images and 3D Lidar point clouds based on 2D and 3D segmentation approaches. Then the segmentation results from different sensors are adaptively fused based on the proposed attention-based semantic fusion module. Finally, the point clouds painted with the fused semantic label are sent to the 3D detector for obtaining the 3D objection results. The effectiveness of the proposed framework has been verified on the large-scale nuScenes detection benchmark by comparing it with three different baselines. The experimental results show that the fusion strategy can significantly improve the detection performance compared to the methods using only point clouds, and the methods using point clouds only painted with 2D segmentation information. Furthermore, the proposed approach outperforms other state-of-the-art methods on the nuScenes testing benchmark.
7.How Well do Feature Visualizations Support Causal Understanding of CNN Activations? ⬇️
One widely used approach towards understanding the inner workings of deep convolutional neural networks is to visualize unit responses via activation maximization. Feature visualizations via activation maximization are thought to provide humans with precise information about the image features that cause a unit to be activated. If this is indeed true, these synthetic images should enable humans to predict the effect of an intervention, such as whether occluding a certain patch of the image (say, a dog's head) changes a unit's activation. Here, we test this hypothesis by asking humans to predict which of two square occlusions causes a larger change to a unit's activation. Both a large-scale crowdsourced experiment and measurements with experts show that on average, the extremely activating feature visualizations by Olah et al. (2017) indeed help humans on this task (
$67 \pm 4%$ accuracy; baseline performance without any visualizations is$60 \pm 3%$ ). However, they do not provide any significant advantage over other visualizations (such as e.g. dataset samples), which yield similar performance ($66 \pm 3%$ to$67 \pm 3%$ accuracy). Taken together, we propose an objective psychophysical task to quantify the benefit of unit-level interpretability methods for humans, and find no evidence that feature visualizations provide humans with better "causal understanding" than simple alternative visualizations.
8.Fine-Tuning StyleGAN2 For Cartoon Face Generation ⬇️
Recent studies have shown remarkable success in the unsupervised image to image (I2I) translation. However, due to the imbalance in the data, learning joint distribution for various domains is still very challenging. Although existing models can generate realistic target images, it's difficult to maintain the structure of the source image. In addition, training a generative model on large data in multiple domains requires a lot of time and computer resources. To address these limitations, we propose a novel image-to-image translation method that generates images of the target domain by finetuning a stylegan2 pretrained model. The stylegan2 model is suitable for unsupervised I2I translation on unbalanced datasets; it is highly stable, produces realistic images, and even learns properly from limited data when applied with simple fine-tuning techniques. Thus, in this paper, we propose new methods to preserve the structure of the source images and generate realistic images in the target domain. The code and results are available at this https URL
9.Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers ⬇️
Accurate prediction of pedestrian and bicyclist paths is integral to the development of reliable autonomous vehicles in dense urban environments. The interactions between vehicle and pedestrian or bicyclist have a significant impact on the trajectories of traffic participants e.g. stopping or turning to avoid collisions. Although recent datasets and trajectory prediction approaches have fostered the development of autonomous vehicles yet the amount of vehicle-pedestrian (bicyclist) interactions modeled are sparse. In this work, we propose Euro-PVI, a dataset of pedestrian and bicyclist trajectories. In particular, our dataset caters more diverse and complex interactions in dense urban scenarios compared to the existing datasets. To address the challenges in predicting future trajectories with dense interactions, we develop a joint inference model that learns an expressive multi-modal shared latent space across agents in the urban scene. This enables our Joint-$\beta$-cVAE approach to better model the distribution of future trajectories. We achieve state of the art results on the nuScenes and Euro-PVI datasets demonstrating the importance of capturing interactions between ego-vehicle and pedestrians (bicyclists) for accurate predictions.
10.Alias-Free Generative Adversarial Networks ⬇️
We observe that despite their hierarchical convolutional nature, the synthesis process of typical generative adversarial networks depends on absolute pixel coordinates in an unhealthy manner. This manifests itself as, e.g., detail appearing to be glued to image coordinates instead of the surfaces of depicted objects. We trace the root cause to careless signal processing that causes aliasing in the generator network. Interpreting all signals in the network as continuous, we derive generally applicable, small architectural changes that guarantee that unwanted information cannot leak into the hierarchical synthesis process. The resulting networks match the FID of StyleGAN2 but differ dramatically in their internal representations, and they are fully equivariant to translation and rotation even at subpixel scales. Our results pave the way for generative models better suited for video and animation.
11.Transformer Meets Convolution: A Bilateral Awareness Net-work for Semantic Segmentation of Very Fine Resolution Ur-ban Scene Images ⬇️
Semantic segmentation from very fine resolution (VFR) urban scene images plays a significant role in several application scenarios including autonomous driving, land cover classification, and urban planning, etc. However, the tremendous details contained in the VFR image severely limit the potential of the existing deep learning approaches. More seriously, the considerable variations in scale and appearance of objects further deteriorate the representational capacity of those se-mantic segmentation methods, leading to the confusion of adjacent objects. Addressing such is-sues represents a promising research field in the remote sensing community, which paves the way for scene-level landscape pattern analysis and decision making. In this manuscript, we pro-pose a bilateral awareness network (BANet) which contains a dependency path and a texture path to fully capture the long-range relationships and fine-grained details in VFR images. Specif-ically, the dependency path is conducted based on the ResT, a novel Transformer backbone with memory-efficient multi-head self-attention, while the texture path is built on the stacked convo-lution operation. Besides, using the linear attention mechanism, a feature aggregation module (FAM) is designed to effectively fuse the dependency features and texture features. Extensive experiments conducted on the three large-scale urban scene image segmentation datasets, i.e., ISPRS Vaihingen dataset, ISPRS Potsdam dataset, and UAVid dataset, demonstrate the effective-ness of our BANet. Specifically, a 64.6% mIoU is achieved on the UAVid dataset.
12.Fairness in Cardiac MR Image Analysis: An Investigation of Bias Due to Data Imbalance in Deep Learning Based Segmentation ⬇️
The subject of "fairness" in artificial intelligence (AI) refers to assessing AI algorithms for potential bias based on demographic characteristics such as race and gender, and the development of algorithms to address this bias. Most applications to date have been in computer vision, although some work in healthcare has started to emerge. The use of deep learning (DL) in cardiac MR segmentation has led to impressive results in recent years, and such techniques are starting to be translated into clinical practice. However, no work has yet investigated the fairness of such models. In this work, we perform such an analysis for racial/gender groups, focusing on the problem of training data imbalance, using a nnU-Net model trained and evaluated on cine short axis cardiac MR data from the UK Biobank dataset, consisting of 5,903 subjects from 6 different racial groups. We find statistically significant differences in Dice performance between different racial groups. To reduce the racial bias, we investigated three strategies: (1) stratified batch sampling, in which batch sampling is stratified to ensure balance between racial groups; (2) fair meta-learning for segmentation, in which a DL classifier is trained to classify race and jointly optimized with the segmentation model; and (3) protected group models, in which a different segmentation model is trained for each racial group. We also compared the results to the scenario where we have a perfectly balanced database. To assess fairness we used the standard deviation (SD) and skewed error ratio (SER) of the average Dice values. Our results demonstrate that the racial bias results from the use of imbalanced training data, and that all proposed bias mitigation strategies improved fairness, with the best SD and SER resulting from the use of protected group models.
13.Co-advise: Cross Inductive Bias Distillation ⬇️
Transformers recently are adapted from the community of natural language processing as a promising substitute of convolution-based neural networks for visual learning tasks. However, its supremacy degenerates given an insufficient amount of training data (e.g., ImageNet). To make it into practical utility, we propose a novel distillation-based method to train vision transformers. Unlike previous works, where merely heavy convolution-based teachers are provided, we introduce lightweight teachers with different architectural inductive biases (e.g., convolution and involution) to co-advise the student transformer. The key is that teachers with different inductive biases attain different knowledge despite that they are trained on the same dataset, and such different knowledge compounds and boosts the student's performance during distillation. Equipped with this cross inductive bias distillation method, our vision transformers (termed as CivT) outperform all previous transformers of the same architecture on ImageNet.
14.Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition ⬇️
In this paper, we present Vision Permutator, a conceptually simple and data efficient MLP-like architecture for visual recognition. By realizing the importance of the positional information carried by 2D feature representations, unlike recent MLP-like models that encode the spatial information along the flattened spatial dimensions, Vision Permutator separately encodes the feature representations along the height and width dimensions with linear projections. This allows Vision Permutator to capture long-range dependencies along one spatial direction and meanwhile preserve precise positional information along the other direction. The resulting position-sensitive outputs are then aggregated in a mutually complementing manner to form expressive representations of the objects of interest. We show that our Vision Permutators are formidable competitors to convolutional neural networks (CNNs) and vision transformers. Without the dependence on spatial convolutions or attention mechanisms, Vision Permutator achieves 81.5% top-1 accuracy on ImageNet without extra large-scale training data (e.g., ImageNet-22k) using only 25M learnable parameters, which is much better than most CNNs and vision transformers under the same model size constraint. When scaling up to 88M, it attains 83.2% top-1 accuracy. We hope this work could encourage research on rethinking the way of encoding spatial information and facilitate the development of MLP-like models. Code is available at this https URL.
15.A new Video Synopsis Based Approach Using Stereo Camera ⬇️
In today's world, the amount of data produced in every field has increased at an unexpected level. In the face of increasing data, the importance of data processing has increased remarkably. Our resource topic is on the processing of video data, which has an important place in increasing data, and the production of summary videos. Within the scope of this resource, a new method for anomaly detection with object-based unsupervised learning has been developed while creating a video summary. By using this method, the video data is processed as pixels and the result is produced as a video segment. The process flow can be briefly summarized as follows. Objects on the video are detected according to their type, and then they are tracked. Then, the tracking history data of the objects are processed, and the classifier is trained with the object type. Thanks to this classifier, anomaly behavior of objects is detected. Video segments are determined by processing video moments containing anomaly behaviors. The video summary is created by extracting the detected video segments from the original video and combining them. The model we developed has been tested and verified separately for single camera and dual camera systems.
16.Open Images V5 Text Annotation and Yet Another Mask Text Spotter ⬇️
A large scale human-labeled dataset plays an important role in creating high quality deep learning models. In this paper we present text annotation for Open Images V5 dataset. To our knowledge it is the largest among publicly available manually created text annotations. Having this annotation we trained a simple Mask-RCNN-based network, referred as Yet Another Mask Text Spotter (YAMTS), which achieves competitive performance or even outperforms current state-of-the-art approaches in some cases on ICDAR2013, ICDAR2015 and Total-Text datasets. Code for text spotting model available online at: this https URL. The model can be exported to OpenVINO-format and run on Intel CPUs.
17.Estimating the Robustness of Classification Models by the Structure of the Learned Feature-Space ⬇️
Over the last decade, the development of deep image classification networks has mostly been driven by the search for the best performance in terms of classification accuracy on standardized benchmarks like ImageNet. More recently, this focus has been expanded by the notion of model robustness, i.e. the generalization abilities of models towards previously unseen changes in the data distribution. While new benchmarks, like ImageNet-C, have been introduced to measure robustness properties, we argue that fixed testsets are only able to capture a small portion of possible data variations and are thus limited and prone to generate new overfitted solutions. To overcome these drawbacks, we suggest to estimate the robustness of a model directly from the structure of its learned feature-space. We introduce robustness indicators which are obtained via unsupervised clustering of latent representations inside a trained classifier and show very high correlations to the model performance on corrupted test data.
18.3D human tongue reconstruction from single "in-the-wild" images ⬇️
3D face reconstruction from a single image is a task that has garnered increased interest in the Computer Vision community, especially due to its broad use in a number of applications such as realistic 3D avatar creation, pose invariant face recognition and face hallucination. Since the introduction of the 3D Morphable Model in the late 90's, we witnessed an explosion of research aiming at particularly tackling this task. Nevertheless, despite the increasing level of detail in the 3D face reconstructions from single images mainly attributed to deep learning advances, finer and highly deformable components of the face such as the tongue are still absent from all 3D face models in the literature, although being very important for the realness of the 3D avatar representations. In this work we present the first, to the best of our knowledge, end-to-end trainable pipeline that accurately reconstructs the 3D face together with the tongue. Moreover, we make this pipeline robust in "in-the-wild" images by introducing a novel GAN method tailored for 3D tongue surface generation. Finally, we make publicly available to the community the first diverse tongue dataset, consisting of 1,800 raw scans of 700 individuals varying in gender, age, and ethnicity backgrounds. As we demonstrate in an extensive series of quantitative as well as qualitative experiments, our model proves to be robust and realistically captures the 3D tongue structure, even in adverse "in-the-wild" conditions.
19.A Label Management Mechanism for Retinal Fundus Image Classification of Diabetic Retinopathy ⬇️
Diabetic retinopathy (DR) remains the most prevalent cause of vision impairment and irreversible blindness in the working-age adults. Due to the renaissance of deep learning (DL), DL-based DR diagnosis has become a promising tool for the early screening and severity grading of DR. However, training deep neural networks (DNNs) requires an enormous amount of carefully labeled data. Noisy label data may be introduced when labeling plenty of data, degrading the performance of models. In this work, we propose a novel label management mechanism (LMM) for the DNN to overcome overfitting on the noisy data. LMM utilizes maximum posteriori probability (MAP) in the Bayesian statistic and time-weighted technique to selectively correct the labels of unclean data, which gradually purify the training data and improve classification performance. Comprehensive experiments on both synthetic noise data (Messidor & our collected DR dataset) and real-world noise data (ANIMAL-10N) demonstrated that LMM could boost performance of models and is superior to three state-of-the-art methods.
20.Deep unsupervised 3D human body reconstruction from a sparse set of landmarks ⬇️
In this paper we propose the first deep unsupervised approach in human body reconstruction to estimate body surface from a sparse set of landmarks, so called DeepMurf. We apply a denoising autoencoder to estimate missing landmarks. Then we apply an attention model to estimate body joints from landmarks. Finally, a cascading network is applied to regress parameters of a statistical generative model that reconstructs body. Our set of proposed loss functions allows us to train the network in an unsupervised way. Results on four public datasets show that our approach accurately reconstructs the human body from real world mocap data.
21.Instance-based Vision Transformer for Subtyping of Papillary Renal Cell Carcinoma in Histopathological Image ⬇️
Histological subtype of papillary (p) renal cell carcinoma (RCC), type 1 vs. type 2, is an essential prognostic factor. The two subtypes of pRCC have a similar pattern, i.e., the papillary architecture, yet some subtle differences, including cellular and cell-layer level patterns. However, the cellular and cell-layer level patterns almost cannot be captured by existing CNN-based models in large-size histopathological images, which brings obstacles to directly applying these models to such a fine-grained classification task. This paper proposes a novel instance-based Vision Transformer (i-ViT) to learn robust representations of histopathological images for the pRCC subtyping task by extracting finer features from instance patches (by cropping around segmented nuclei and assigning predicted grades). The proposed i-ViT takes top-K instances as input and aggregates them for capturing both the cellular and cell-layer level patterns by a position-embedding layer, a grade-embedding layer, and a multi-head multi-layer self-attention module. To evaluate the performance of the proposed framework, experienced pathologists are invited to selected 1162 regions of interest from 171 whole slide images of type 1 and type 2 pRCC. Experimental results show that the proposed method achieves better performance than existing CNN-based models with a significant margin.
22.Mutual-Information Based Few-Shot Classification ⬇️
We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions for a given few-shot task, in conjunction with a supervision loss based on the support set. We motivate our transductive loss by deriving a formal relation between the classification accuracy and mutual-information maximization. Furthermore, we propose a new alternating-direction solver, which substantially speeds up transductive inference over gradient-based optimization, while yielding competitive accuracy. We also provide a convergence analysis of our solver based on Zangwill's theory and bound-optimization arguments. TIM inference is modular: it can be used on top of any base-training feature extractor. Following standard transductive few-shot settings, our comprehensive experiments demonstrate that TIM outperforms state-of-the-art methods significantly across various datasets and networks, while used on top of a fixed feature extractor trained with simple cross-entropy on the base classes, without resorting to complex meta-learning schemes. It consistently brings between 2 % and 5 % improvement in accuracy over the best performing method, not only on all the well-established few-shot benchmarks but also on more challenging scenarios, with random tasks, domain shift and larger numbers of classes, as in the recently introduced META-DATASET. Our code is publicly available at this https URL. We also publicly release a standalone PyTorch implementation of META-DATASET, along with additional benchmarking results, at this https URL.
23.Sentinel-1 and Sentinel-2 Spatio-Temporal Data Fusion for Clouds Removal ⬇️
The abundance of clouds, located both spatially and temporally, often makes remote sensing applications with optical images difficult or even impossible. In this manuscript, a novel method for clouds-corrupted optical image restoration has been presented and developed, based on a joint data fusion paradigm, where three deep neural networks have been combined in order to fuse spatio-temporal features extracted from Sentinel-1 and Sentinel-2 time-series of data. It is worth highlighting that both the code and the dataset have been implemented from scratch and made available to interested research for further analysis and investigation.
24.Image-to-Image Translation of Synthetic Samples for Rare Classes ⬇️
The natural world is long-tailed: rare classes are observed orders of magnitudes less frequently than common ones, leading to highly-imbalanced data where rare classes can have only handfuls of examples. Learning from few examples is a known challenge for deep learning based classification algorithms, and is the focus of the field of low-shot learning. One potential approach to increase the training data for these rare classes is to augment the limited real data with synthetic samples. This has been shown to help, but the domain shift between real and synthetic hinders the approaches' efficacy when tested on real data.
We explore the use of image-to-image translation methods to close the domain gap between synthetic and real imagery for animal species classification in data collected from camera traps: motion-activated static cameras used to monitor wildlife. We use low-level feature alignment between source and target domains to make synthetic data for a rare species generated using a graphics engine more "realistic". Compared against a system augmented with unaligned synthetic data, our experiments show a considerable decrease in classification error rates on a rare species.
25.Real-time Instance Segmentation with Discriminative Orientation Maps ⬇️
Although instance segmentation has made considerable advancement over recent years, it's still a challenge to design high accuracy algorithms with real-time performance. In this paper, we propose a real-time instance segmentation framework termed OrienMask. Upon the one-stage object detector YOLOv3, a mask head is added to predict some discriminative orientation maps, which are explicitly defined as spatial offset vectors for both foreground and background pixels. Thanks to the discrimination ability of orientation maps, masks can be recovered without the need for extra foreground segmentation. All instances that match with the same anchor size share a common orientation map. This special sharing strategy reduces the amortized memory utilization for mask predictions but without loss of mask granularity. Given the surviving box predictions after NMS, instance masks can be concurrently constructed from the corresponding orientation maps with low complexity. Owing to the concise design for mask representation and its effective integration with the anchor-based object detector, our method is qualified under real-time conditions while maintaining competitive accuracy. Experiments on COCO benchmark show that OrienMask achieves 34.8 mask AP at the speed of 42.7 fps evaluated with a single RTX 2080 Ti. The code is available at this https URL.
26.Vision-based Behavioral Recognition of Novelty Preference in Pigs ⬇️
Behavioral scoring of research data is crucial for extracting domain-specific metrics but is bottlenecked on the ability to analyze enormous volumes of information using human labor. Deep learning is widely viewed as a key advancement to relieve this bottleneck. We identify one such domain, where deep learning can be leveraged to alleviate the process of manual scoring. Novelty preference paradigms have been widely used to study recognition memory in pigs, but analysis of these videos requires human intervention. We introduce a subset of such videos in the form of the 'Pig Novelty Preference Behavior' (PNPB) dataset that is fully annotated with pig actions and keypoints. In order to demonstrate the application of state-of-the-art action recognition models on this dataset, we compare LRCN, C3D, and TSM on the basis of various analytical metrics and discuss common pitfalls of the models. Our methods achieve an accuracy of 93% and a mean Average Precision of 96% in estimating piglet behavior.
We open-source our code and annotated dataset at this https URL
27.Region-Aware Network: Model Human's Top-Down Visual Perception Mechanism for Crowd Counting ⬇️
Background noise and scale variation are common problems that have been long recognized in crowd counting. Humans glance at a crowd image and instantly know the approximate number of human and where they are through attention the crowd regions and the congestion degree of crowd regions with a global receptive filed. Hence, in this paper, we propose a novel feedback network with Region-Aware block called RANet by modeling human's Top-Down visual perception mechanism. Firstly, we introduce a feedback architecture to generate priority maps that provide prior about candidate crowd regions in input images. The prior enables the RANet pay more attention to crowd regions. Then we design Region-Aware block that could adaptively encode the contextual information into input images through global receptive field. More specifically, we scan the whole input images and its priority maps in the form of column vector to obtain a relevance matrix estimating their similarity. The relevance matrix obtained would be utilized to build global relationships between pixels. Our method outperforms state-of-the-art crowd counting methods on several public datasets.
28.Neural Fashion Image Captioning : Accounting for Data Diversity ⬇️
Image captioning has increasingly large domains of application, and fashion is not an exception. Having automatic item descriptions is of great interest for fashion web platforms hosting sometimes hundreds of thousands of images. This paper is one of the first tackling image captioning for fashion images. To contribute addressing dataset diversity issues, we introduced the InFashAIv1 dataset containing almost 16.000 African fashion item images with their titles, prices and general descriptions. We also used the well known DeepFashion dataset in addition to InFashAIv1. Captions are generated using the \textit{Show and Tell} model made of CNN encoder and RNN Decoder. We showed that jointly training the model on both datasets improves captions quality for African style fashion images, suggesting a transfer learning from Western style data. The InFashAIv1 dataset is released on \href{this https URL}{Github} to encourage works with more diversity inclusion.
29.Bootstrap Representation Learning for Segmentation on Medical Volumes and Sequences ⬇️
In this work, we propose a novel straightforward method for medical volume and sequence segmentation with limited annotations. To avert laborious annotating, the recent success of self-supervised learning(SSL) motivates the pre-training on unlabeled data. Despite its success, it is still challenging to adapt typical SSL methods to volume/sequence segmentation, due to their lack of mining on local semantic discrimination and rare exploitation on volume and sequence structures. Based on the continuity between slices/frames and the common spatial layout of organs across volumes/sequences, we introduced a novel bootstrap self-supervised representation learning method by leveraging the predictable possibility of neighboring slices. At the core of our method is a simple and straightforward dense self-supervision on the predictions of local representations and a strategy of predicting locals based on global context, which enables stable and reliable supervision for both global and local representation mining among volumes. Specifically, we first proposed an asymmetric network with an attention-guided predictor to enforce distance-specific prediction and supervision on slices within and across volumes/sequences. Secondly, we introduced a novel prototype-based foreground-background calibration module to enhance representation consistency. The two parts are trained jointly on labeled and unlabeled data. When evaluated on three benchmark datasets of medical volumes and sequences, our model outperforms existing methods with a large margin of 4.5% DSC on ACDC, 1.7% on Prostate, and 2.3% on CAMUS. Intensive evaluations reveals the effectiveness and superiority of our method.
30.PatentNet: A Large-Scale Incomplete Multiview, Multimodal, Multilabel Industrial Goods Image Database ⬇️
In deep learning area, large-scale image datasets bring a breakthrough in the success of object recognition and retrieval. Nowadays, as the embodiment of innovation, the diversity of the industrial goods is significantly larger, in which the incomplete multiview, multimodal and multilabel are different from the traditional dataset. In this paper, we introduce an industrial goods dataset, namely PatentNet, with numerous highly diverse, accurate and detailed annotations of industrial goods images, and corresponding texts. In PatentNet, the images and texts are sourced from design patent. Within over 6M images and corresponding texts of industrial goods labeled manually checked by professionals, PatentNet is the first ongoing industrial goods image database whose varieties are wider than industrial goods datasets used previously for benchmarking. PatentNet organizes millions of images into 32 classes and 219 subclasses based on the Locarno Classification Agreement. Through extensive experiments on image classification, image retrieval and incomplete multiview clustering, we demonstrate that our PatentNet is much more diverse, complex, and challenging, enjoying higher potentials than existing industrial image datasets. Furthermore, the characteristics of incomplete multiview, multimodal and multilabel in PatentNet are able to offer unparalleled opportunities in the artificial intelligence community and beyond.
31.Exploiting Negative Learning for Implicit Pseudo Label Rectification in Source-Free Domain Adaptive Semantic Segmentation ⬇️
It is desirable to transfer the knowledge stored in a well-trained source model onto non-annotated target domain in the absence of source data. However, state-of-the-art methods for source free domain adaptation (SFDA) are subject to strict limits: 1) access to internal specifications of source models is a must; and 2) pseudo labels should be clean during self-training, making critical tasks relying on semantic segmentation unreliable. Aiming at these pitfalls, this study develops a domain adaptive solution to semantic segmentation with pseudo label rectification (namely \textit{PR-SFDA}), which operates in two phases: 1) \textit{Confidence-regularized unsupervised learning}: Maximum squares loss applies to regularize the target model to ensure the confidence in prediction; and 2) \textit{Noise-aware pseudo label learning}: Negative learning enables tolerance to noisy pseudo labels in training, meanwhile positive learning achieves fast convergence. Extensive experiments have been performed on domain adaptive semantic segmentation benchmark, \textit{GTA5
$\to$ Cityscapes}. Overall, \textit{PR-SFDA} achieves a performance of 49.0 mIoU, which is very close to that of the state-of-the-art counterparts. Note that the latter demand accesses to the source model's internal specifications, whereas the \textit{PR-SFDA} solution needs none as a sharp contrast.
32.LegoFormer: Transformers for Block-by-Block Multi-view 3D Reconstruction ⬇️
Most modern deep learning-based multi-view 3D reconstruction techniques use RNNs or fusion modules to combine information from multiple images after encoding them. These two separate steps have loose connections and do not consider all available information while encoding each view. We propose LegoFormer, a transformer-based model that unifies object reconstruction under a single framework and parametrizes the reconstructed occupancy grid by its decomposition factors. This reformulation allows the prediction of an object as a set of independent structures then aggregated to obtain the final reconstruction. Experiments conducted on ShapeNet display the competitive performance of our network with respect to the state-of-the-art methods. We also demonstrate how the use of self-attention leads to increased interpretability of the model output.
33.Reachability Analysis of Convolutional Neural Networks ⬇️
Deep convolutional neural networks have been widely employed as an effective technique to handle complex and practical problems. However, one of the fundamental problems is the lack of formal methods to analyze their behavior. To address this challenge, we propose an approach to compute the exact reachable sets of a network given an input domain, where the reachable set is represented by the face lattice structure. Besides the computation of reachable sets, our approach is also capable of backtracking to the input domain given an output reachable set. Therefore, a full analysis of a network's behavior can be realized. In addition, an approach for fast analysis is also introduced, which conducts fast computation of reachable sets by considering selected sensitive neurons in each layer. The exact pixel-level reachability analysis method is evaluated on a CNN for the CIFAR10 dataset and compared to related works. The fast analysis method is evaluated over a CNN CIFAR10 dataset and VGG16 architecture for the ImageNet dataset.
34.Automatic Head Overcoat Thickness Measure with NASNet-Large-Decoder Net ⬇️
Transmission electron microscopy (TEM) is one of the primary tools to show microstructural characterization of materials as well as film thickness. However, manual determination of film thickness from TEM images is time-consuming as well as subjective, especially when the films in question are very thin and the need for measurement precision is very high. Such is the case for head overcoat (HOC) thickness measurements in the magnetic hard disk drive industry. It is therefore necessary to develop software to automatically measure HOC thickness. In this paper, for the first time, we propose a HOC layer segmentation method using NASNet-Large as an encoder and then followed by a decoder architecture, which is one of the most commonly used architectures in deep learning for image segmentation. To further improve segmentation results, we are the first to propose a post-processing layer to remove irrelevant portions in the segmentation result. To measure the thickness of the segmented HOC layer, we propose a regressive convolutional neural network (RCNN) model as well as orthogonal thickness calculation methods. Experimental results demonstrate a higher dice score for our model which has lower mean squared error and outperforms current state-of-the-art manual measurement.
35.Volume Rendering of Neural Implicit Surfaces ⬇️
Neural volume rendering became increasingly popular recently due to its success in synthesizing novel views of a scene from a sparse set of input images. So far, the geometry learned by neural volume rendering techniques was modeled using a generic density function. Furthermore, the geometry itself was extracted using an arbitrary level set of the density function leading to a noisy, often low fidelity reconstruction. The goal of this paper is to improve geometry representation and reconstruction in neural volume rendering. We achieve that by modeling the volume density as a function of the geometry. This is in contrast to previous work modeling the geometry as a function of the volume density. In more detail, we define the volume density function as Laplace's cumulative distribution function (CDF) applied to a signed distance function (SDF) representation. This simple density representation has three benefits: (i) it provides a useful inductive bias to the geometry learned in the neural volume rendering process; (ii) it facilitates a bound on the opacity approximation error, leading to an accurate sampling of the viewing ray. Accurate sampling is important to provide a precise coupling of geometry and radiance; and (iii) it allows efficient unsupervised disentanglement of shape and appearance in volume rendering. Applying this new density representation to challenging scene multiview datasets produced high quality geometry reconstructions, outperforming relevant baselines. Furthermore, switching shape and appearance between scenes is possible due to the disentanglement of the two.
36.Listen to Your Favorite Melodies with img2Mxml, Producing MusicXML from Sheet Music Image by Measure-based Multimodal Deep Learning-driven Assembly ⬇️
Deep learning has recently been applied to optical music recognition (OMR). However, currently OMR processing from various sheet music images still lacks precision to be widely applicable. Here, we present an MMdA (Measure-based Multimodal deep learning (DL)-driven Assembly) method allowing for end-to-end OMR processing from various images including inclined photo images. Using this method, measures are extracted by a deep learning model, aligned, and resized to be used for inference of given musical symbol components by using multiple deep learning models in sequence or in parallel. Use of each standardized measure enables efficient training of the models and accurate adjustment of five staff lines in each measure. Multiple musical symbol component category models with a small number of feature types can represent a diverse set of notes and other musical symbols including chords. This MMdA method provides a solution to end-to-end OMR processing with precision.
37.The Neurally-Guided Shape Parser: A Monte Carlo Method for Hierarchical Labeling of Over-segmented 3D Shapes ⬇️
Many learning-based 3D shape semantic segmentation methods assign labels to shape atoms (e.g. points in a point cloud or faces in a mesh) with a single-pass approach trained in an end-to-end fashion. Such methods achieve impressive performance but require large amounts of labeled training data. This paradigm entangles two separable subproblems: (1) decomposing a shape into regions and (2) assigning semantic labels to these regions. We claim that disentangling these subproblems reduces the labeled data burden: (1) region decomposition requires no semantic labels and could be performed in an unsupervised fashion, and (2) labeling shape regions instead of atoms results in a smaller search space and should be learnable with less labeled training data. In this paper, we investigate this second claim by presenting the Neurally-Guided Shape Parser (NGSP), a method that learns how to assign semantic labels to regions of an over-segmented 3D shape. We solve this problem via MAP inference, modeling the posterior probability of a labeling assignment conditioned on an input shape. We employ a Monte Carlo importance sampling approach guided by a neural proposal network, a search-based approach made feasible by assuming the input shape is decomposed into discrete regions. We evaluate NGSP on the task of hierarchical semantic segmentation on manufactured 3D shapes from PartNet. We find that NGSP delivers significant performance improvements over baselines that learn to label shape atoms and then aggregate predictions for each shape region, especially in low-data regimes. Finally, we demonstrate that NGSP is robust to region granularity, as it maintains strong segmentation performance even as the regions undergo significant corruption.
38.Team PyKale (xy9) Submission to the EPIC-Kitchens 2021 Unsupervised Domain Adaptation Challenge for Action Recognition ⬇️
This report describes the technical details of our submission to the EPIC-Kitchens 2021 Unsupervised Domain Adaptation Challenge for Action Recognition. The EPIC-Kitchens dataset is more difficult than other video domain adaptation datasets due to multi-tasks with more modalities. Firstly, to participate in the challenge, we employ a transformer to capture the spatial information from each modality. Secondly, we employ a temporal attention module to model temporal-wise inter-dependency. Thirdly, we employ the adversarial domain adaptation network to learn the general features between labeled source and unlabeled target domain. Finally, we incorporate multiple modalities to improve the performance by a three-stream network with late fusion. Our network achieves the comparable performance with the state-of-the-art baseline T$A^3$N and outperforms the baseline on top-1 accuracy for verb class and top-5 accuracies for all three tasks which are verb, noun and action. Under the team name xy9, our submission achieved 5th place in terms of top-1 accuracy for verb class and all top-5 accuracies.
39.On Matrix Factorizations in Subspace Clustering ⬇️
This article explores subspace clustering algorithms using CUR decompositions, and examines the effect of various hyperparameters in these algorithms on clustering performance on two real-world benchmark datasets, the Hopkins155 motion segmentation dataset and the Yale face dataset. Extensive experiments are done for a variety of sampling methods and oversampling parameters for these datasets, and some guidelines for parameter choices are given for practical applications.
40.Transfer Learning of Deep Spatiotemporal Networks to Model Arbitrarily Long Videos of Seizures ⬇️
Detailed analysis of seizure semiology, the symptoms and signs which occur during a seizure, is critical for management of epilepsy patients. Inter-rater reliability using qualitative visual analysis is often poor for semiological features. Therefore, automatic and quantitative analysis of video-recorded seizures is needed for objective assessment.
We present GESTURES, a novel architecture combining convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to learn deep representations of arbitrarily long videos of epileptic seizures.
We use a spatiotemporal CNN (STCNN) pre-trained on large human action recognition (HAR) datasets to extract features from short snippets (approx. 0.5 s) sampled from seizure videos. We then train an RNN to learn seizure-level representations from the sequence of features.
We curated a dataset of seizure videos from 68 patients and evaluated GESTURES on its ability to classify seizures into focal onset seizures (FOSs) (N = 106) vs. focal to bilateral tonic-clonic seizures (TCSs) (N = 77), obtaining an accuracy of 98.9% using bidirectional long short-term memory (BLSTM) units.
We demonstrate that an STCNN trained on a HAR dataset can be used in combination with an RNN to accurately represent arbitrarily long videos of seizures. GESTURES can provide accurate seizure classification by modeling sequences of semiologies.
41.P2T: Pyramid Pooling Transformer for Scene Understanding ⬇️
This paper jointly resolves two problems in vision transformer: i) the computation of Multi-Head Self-Attention (MHSA) has high computational/space complexity; ii) recent vision transformer networks are overly tuned for image classification, ignoring the difference between image classification (simple scenarios, more similar to NLP) and downstream scene understanding tasks (complicated scenarios, rich structural and contextual information). To this end, we note that pyramid pooling has been demonstrated to be effective in various vision tasks owing to its powerful context abstraction, and its natural property of spatial invariance is suitable to address the loss of structural information (problem ii)). Hence, we propose to adapt pyramid pooling to MHSA for alleviating its high requirement on computational resources (problem i)). In this way, this pooling-based MHSA can well address the above two problems and is thus flexible and powerful for downstream scene understanding tasks. Plugged with our pooling-based MHSA, we build a downstream-task-oriented transformer network, dubbed Pyramid Pooling Transformer (P2T). Extensive experiments demonstrate that, when applied P2T as the backbone network, it shows substantial superiority in various downstream scene understanding tasks such as semantic segmentation, object detection, instance segmentation, and visual saliency detection, compared to previous CNN- and transformer-based networks. The code will be released at this https URL. Note that this technical report will keep updating.
42.Feature Alignment for Approximated Reversibility in Neural Networks ⬇️
We introduce feature alignment, a technique for obtaining approximate reversibility in artificial neural networks. By means of feature extraction, we can train a neural network to learn an estimated map for its reverse process from outputs to inputs. Combined with variational autoencoders, we can generate new samples from the same statistics as the training data. Improvements of the results are obtained by using concepts from generative adversarial networks. Finally, we show that the technique can be modified for training neural networks locally, saving computational memory resources. Applying these techniques, we report results for three vision generative tasks: MNIST, CIFAR-10, and celebA.
43.Diabetic Retinopathy Detection using Ensemble Machine Learning ⬇️
Diabetic Retinopathy (DR) is among the worlds leading vision loss causes in diabetic patients. DR is a microvascular disease that affects the eye retina, which causes vessel blockage and therefore cuts the main source of nutrition for the retina tissues. Treatment for this visual disorder is most effective when it is detected in its earliest stages, as severe DR can result in irreversible blindness. Nonetheless, DR identification requires the expertise of Ophthalmologists which is often expensive and time-consuming. Therefore, automatic detection systems were introduced aiming to facilitate the identification process, making it available globally in a time and cost-efficient manner. However, due to the limited reliable datasets and medical records for this particular eye disease, the obtained predictions accuracies were relatively unsatisfying for eye specialists to rely on them as diagnostic systems. Thus, we explored an ensemble-based learning strategy, merging a substantial selection of well-known classification algorithms in one sophisticated diagnostic model. The proposed framework achieved the highest accuracy rates among all other common classification algorithms in the area. 4 subdatasets were generated to contain the top 5 and top 10 features of the Messidor dataset, selected by InfoGainEval. and WrapperSubsetEval., accuracies of 70.7% and 75.1% were achieved on the InfoGainEval. top 5 and original dataset respectively. The results imply the impressive performance of the subdataset, which significantly conduces to a less complex classification process
44.Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation ⬇️
Reflecting on the last few years, the biggest breakthroughs in deep reinforcement learning (RL) have been in the discrete action domain. Robotic manipulation, however, is inherently a continuous control environment, but these continuous control reinforcement learning algorithms often depend on actor-critic methods that are sample-inefficient and inherently difficult to train, due to the joint optimisation of the actor and critic. To that end, we explore how we can bring the stability of discrete action RL algorithms to the robot manipulation domain. We extend the recently released ARM algorithm, by replacing the continuous next-best pose agent with a discrete next-best pose agent. Discretisation of rotation is trivial given its bounded nature, while translation is inherently unbounded, making discretisation difficult. We formulate the translation prediction as the voxel prediction problem by discretising the 3D space; however, voxelisation of a large workspace is memory intensive and would not work with a high density of voxels, crucial to obtaining the resolution needed for robotic manipulation. We therefore propose to apply this voxel prediction in a coarse-to-fine manner by gradually increasing the resolution. In each step, we extract the highest valued voxel as the predicted location, which is then used as the centre of the higher-resolution voxelisation in the next step. This coarse-to-fine prediction is applied over several steps, giving a near-lossless prediction of the translation. We show that our new coarse-to-fine algorithm is able to accomplish RLBench tasks much more efficiently than the continuous control equivalent, and even train some real-world tasks, tabular rasa, in less than 7 minutes, with only 3 demonstrations. Moreover, we show that by moving to a voxel representation, we are able to easily incorporate observations from multiple cameras.
45.FoldIt: Haustral Folds Detection and Segmentation in Colonoscopy Videos ⬇️
Haustral folds are colon wall protrusions implicated for high polyp miss rate during optical colonoscopy procedures. If segmented accurately, haustral folds can allow for better estimation of missed surface and can also serve as valuable landmarks for registering pre-treatment virtual (CT) and optical colonoscopies, to guide navigation towards the anomalies found in pre-treatment scans. We present a novel generative adversarial network, FoldIt, for feature-consistent image translation of optical colonoscopy videos to virtual colonoscopy renderings with haustral fold overlays. A new transitive loss is introduced in order to leverage ground truth information between haustral fold annotations and virtual colonoscopy renderings. We demonstrate the effectiveness of our model on real challenging optical colonoscopy videos as well as on textured virtual colonoscopy videos with clinician-verified haustral fold annotations. All code and scripts to reproduce the experiments of this paper will be made available via our Computational Endoscopy Platform at this https URL.
46.High-Throughput Precision Phenotyping of Left Ventricular Hypertrophy with Cardiovascular Deep Learning ⬇️
Left ventricular hypertrophy (LVH) results from chronic remodeling caused by a broad range of systemic and cardiovascular disease including hypertension, aortic stenosis, hypertrophic cardiomyopathy, and cardiac amyloidosis. Early detection and characterization of LVH can significantly impact patient care but is limited by under-recognition of hypertrophy, measurement error and variability, and difficulty differentiating etiologies of LVH. To overcome this challenge, we present EchoNet-LVH - a deep learning workflow that automatically quantifies ventricular hypertrophy with precision equal to human experts and predicts etiology of LVH. Trained on 28,201 echocardiogram videos, our model accurately measures intraventricular wall thickness (mean absolute error [MAE] 1.4mm, 95% CI 1.2-1.5mm), left ventricular diameter (MAE 2.4mm, 95% CI 2.2-2.6mm), and posterior wall thickness (MAE 1.2mm, 95% CI 1.1-1.3mm) and classifies cardiac amyloidosis (area under the curve of 0.83) and hypertrophic cardiomyopathy (AUC 0.98) from other etiologies of LVH. In external datasets from independent domestic and international healthcare systems, EchoNet-LVH accurately quantified ventricular parameters (R2 of 0.96 and 0.90 respectively) and detected cardiac amyloidosis (AUC 0.79) and hypertrophic cardiomyopathy (AUC 0.89) on the domestic external validation site. Leveraging measurements across multiple heart beats, our model can more accurately identify subtle changes in LV geometry and its causal etiologies. Compared to human experts, EchoNet-LVH is fully automated, allowing for reproducible, precise measurements, and lays the foundation for precision diagnosis of cardiac hypertrophy. As a resource to promote further innovation, we also make publicly available a large dataset of 23,212 annotated echocardiogram videos.
47.Multi-modal and frequency-weighted tensor nuclear norm for hyperspectral image denoising ⬇️
Low-rankness is important in the hyperspectral image (HSI) denoising tasks. The tensor nuclear norm (TNN), defined based on the tensor singular value decomposition, is a state-of-the-art method to describe the low-rankness of HSI. However, TNN ignores some of the physical meanings of HSI in tackling the denoising tasks, leading to suboptimal denoising performance. In this paper, we propose the multi-modal and frequency-weighted tensor nuclear norm (MFWTNN) and the non-convex MFWTNN for HSI denoising tasks. Firstly, we investigate the physical meaning of frequency components and reconsider their weights to improve the low-rank representation ability of TNN. Meanwhile, we also consider the correlation among two spatial dimensions and the spectral dimension of HSI and combine the above improvements to TNN to propose MFWTNN. Secondly, we use non-convex functions to approximate the rank function of the frequency tensor and propose the NonMFWTNN to relax the MFWTNN better. Besides, we adaptively choose bigger weights for slices mainly containing noise information and smaller weights for slices containing profile information. Finally, we develop the efficient alternating direction method of multiplier (ADMM) based algorithm to solve the proposed models, and the effectiveness of our models are substantiated in simulated and real HSI datasets.
48.STRESS: Super-Resolution for Dynamic Fetal MRI using Self-Supervised Learning ⬇️
Fetal motion is unpredictable and rapid on the scale of conventional MR scan times. Therefore, dynamic fetal MRI, which aims at capturing fetal motion and dynamics of fetal function, is limited to fast imaging techniques with compromises in image quality and resolution. Super-resolution for dynamic fetal MRI is still a challenge, especially when multi-oriented stacks of image slices for oversampling are not available and high temporal resolution for recording the dynamics of the fetus or placenta is desired. Further, fetal motion makes it difficult to acquire high-resolution images for supervised learning methods. To address this problem, in this work, we propose STRESS (Spatio-Temporal Resolution Enhancement with Simulated Scans), a self-supervised super-resolution framework for dynamic fetal MRI with interleaved slice acquisitions. Our proposed method simulates an interleaved slice acquisition along the high-resolution axis on the originally acquired data to generate pairs of low- and high-resolution images. Then, it trains a super-resolution network by exploiting both spatial and temporal correlations in the MR time series, which is used to enhance the resolution of the original data. Evaluations on both simulated and in utero data show that our proposed method outperforms other self-supervised super-resolution methods and improves image quality, which is beneficial to other downstream tasks and evaluations.
49.Learning from Pseudo Lesion: A Self-supervised Framework for COVID-19 Diagnosis ⬇️
The Coronavirus disease 2019 (COVID-19) has rapidly spread all over the world since its first report in December 2019 and thoracic computed tomography (CT) has become one of the main tools for its diagnosis. In recent years, deep learning-based approaches have shown impressive performance in myriad image recognition tasks. However, they usually require a large number of annotated data for training. Inspired by Ground Glass Opacity (GGO), a common finding in COIVD-19 patient's CT scans, we proposed in this paper a novel self-supervised pretraining method based on pseudo lesions generation and restoration for COVID-19 diagnosis. We used Perlin noise, a gradient noise based mathematical model, to generate lesion-like patterns, which were then randomly pasted to the lung regions of normal CT images to generate pseudo COVID-19 images. The pairs of normal and pseudo COVID-19 images were then used to train an encoder-decoder architecture based U-Net for image restoration, which does not require any labelled data. The pretrained encoder was then fine-tuned using labelled data for COVID-19 diagnosis task. Two public COVID-19 diagnosis datasets made up of CT images were employed for evaluation. Comprehensive experimental results demonstrated that the proposed self-supervised learning approach could extract better feature representation for COVID-19 diagnosis and the accuracy of the proposed method outperformed the supervised model pretrained on large scale images by 6.57% and 3.03% on SARS-CoV-2 dataset and Jinan COVID-19 dataset, respectively.
50.Behavior Mimics Distribution: Combining Individual and Group Behaviors for Federated Learning ⬇️
Federated Learning (FL) has become an active and promising distributed machine learning paradigm. As a result of statistical heterogeneity, recent studies clearly show that the performance of popular FL methods (e.g., FedAvg) deteriorates dramatically due to the client drift caused by local updates. This paper proposes a novel Federated Learning algorithm (called IGFL), which leverages both Individual and Group behaviors to mimic distribution, thereby improving the ability to deal with heterogeneity. Unlike existing FL methods, our IGFL can be applied to both client and server optimization. As a by-product, we propose a new attention-based federated learning in the server optimization of IGFL. To the best of our knowledge, this is the first time to incorporate attention mechanisms into federated optimization. We conduct extensive experiments and show that IGFL can significantly improve the performance of existing federated learning methods. Especially when the distributions of data among individuals are diverse, IGFL can improve the classification accuracy by about 13% compared with prior baselines.
51.Collaborative Visual Inertial SLAM for Multiple Smart Phones ⬇️
The efficiency and accuracy of mapping are crucial in a large scene and long-term AR applications. Multi-agent cooperative SLAM is the precondition of multi-user AR interaction. The cooperation of multiple smart phones has the potential to improve efficiency and robustness of task completion and can complete tasks that a single agent cannot do. However, it depends on robust communication, efficient location detection, robust mapping, and efficient information sharing among agents. We propose a multi-intelligence collaborative monocular visual-inertial SLAM deployed on multiple ios mobile devices with a centralized architecture. Each agent can independently explore the environment, run a visual-inertial odometry module online, and then send all the measurement information to a central server with higher computing resources. The server manages all the information received, detects overlapping areas, merges and optimizes the map, and shares information with the agents when needed. We have verified the performance of the system in public datasets and real environments. The accuracy of mapping and fusion of the proposed system is comparable to VINS-Mono which requires higher computing resources.
52.A Review of Assistive Technologies for Activities of Daily Living of Elderly ⬇️
One of the distinct features of this century has been the population of older adults which has been on a constant rise. Elderly people have several needs and requirements due to physical disabilities, cognitive issues, weakened memory and disorganized behavior, that they face with increasing age. The extent of these limitations also differs according to the varying diversities in elderly, which include age, gender, background, experience, skills, knowledge and so on. These varying needs and challenges with increasing age, limits abilities of older adults to perform Activities of Daily Living (ADLs) in an independent manner. To add to it, the shortage of caregivers creates a looming need for technology-based services for elderly people, to assist them in performing their daily routine tasks to sustain their independent living and active aging. To address these needs, this work consists of making three major contributions in this field. First, it provides a rather comprehensive review of assisted living technologies aimed at helping elderly people to perform ADLs. Second, the work discusses the challenges identified through this review, that currently exist in the context of implementation of assisted living services for elderly care in Smart Homes and Smart Cities. Finally, the work also outlines an approach for implementation, extension and integration of the existing works in this field for development of a much-needed framework that can provide personalized assistance and user-centered behavior interventions to elderly as per their varying and ever-changing needs.
53.Deformed2Self: Self-Supervised Denoising for Dynamic Medical Imaging ⬇️
Image denoising is of great importance for medical imaging system, since it can improve image quality for disease diagnosis and downstream image analyses. In a variety of applications, dynamic imaging techniques are utilized to capture the time-varying features of the subject, where multiple images are acquired for the same subject at different time points. Although signal-to-noise ratio of each time frame is usually limited by the short acquisition time, the correlation among different time frames can be exploited to improve denoising results with shared information across time frames. With the success of neural networks in computer vision, supervised deep learning methods show prominent performance in single-image denoising, which rely on large datasets with clean-vs-noisy image pairs. Recently, several self-supervised deep denoising models have been proposed, achieving promising results without needing the pairwise ground truth of clean images. In the field of multi-image denoising, however, very few works have been done on extracting correlated information from multiple slices for denoising using self-supervised deep learning methods. In this work, we propose Deformed2Self, an end-to-end self-supervised deep learning framework for dynamic imaging denoising. It combines single-image and multi-image denoising to improve image quality and use a spatial transformer network to model motion between different slices. Further, it only requires a single noisy image with a few auxiliary observations at different time frames for training and inference. Evaluations on phantom and in vivo data with different noise statistics show that our method has comparable performance to other state-of-the-art unsupervised or self-supervised denoising methods and outperforms under high noise levels.
54.APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor Cores ⬇️
Over the years, accelerating neural networks with quantization has been widely studied. Unfortunately, prior efforts with diverse precisions (e.g., 1-bit weights and 2-bit activations) are usually restricted by limited precision support on GPUs (e.g., int1 and int4). To break such restrictions, we introduce the first Arbitrary Precision Neural Network framework (APNN-TC) to fully exploit quantization benefits on Ampere GPU Tensor Cores. Specifically, APNN-TC first incorporates a novel emulation algorithm to support arbitrary short bit-width computation with int1 compute primitives and XOR/AND Boolean operations. Second, APNN-TC integrates arbitrary precision layer designs to efficiently map our emulation algorithm to Tensor Cores with novel batching strategies and specialized memory organization. Third, APNN-TC embodies a novel arbitrary precision NN design to minimize memory access across layers and further improve performance. Extensive evaluations show that APNN-TC can achieve significant speedup over CUTLASS kernels and various NN models, such as ResNet and VGG.
55.CxSE: Chest X-ray Slow Encoding CNN forCOVID-19 Diagnosis ⬇️
The coronavirus continues to disrupt our everyday lives as it spreads at an exponential rate. It needs to be detected quickly in order to quarantine positive patients so as to avoid further spread. This work proposes a new convolutional neural network (CNN) architecture called 'slow Encoding CNN. The proposed model's best performance wrt Sensitivity, Positive Predictive Value (PPV) found to be SP=0.67, PP=0.98, SN=0.96, and PN=0.52 on AI AGAINST COVID19 - Screening X-ray images for COVID-19 Infections competition's test data samples. SP and PP stand for the Sensitivity and PPV of the COVID-19 positive class, while PN and SN stand for the Sensitivity and PPV of the COVID-19 negative class.
56.Towards Consistent Predictive Confidence through Fitted Ensembles ⬇️
Deep neural networks are behind many of the recent successes in machine learning applications. However, these models can produce overconfident decisions while encountering out-of-distribution (OOD) examples or making a wrong prediction. This inconsistent predictive confidence limits the integration of independently-trained learning models into a larger system. This paper introduces separable concept learning framework to realistically measure the performance of classifiers in presence of OOD examples. In this setup, several instances of a classifier are trained on different parts of a partition of the set of classes. Later, the performance of the combination of these models is evaluated on a separate test set. Unlike current OOD detection techniques, this framework does not require auxiliary OOD datasets and does not separate classification from detection performance. Furthermore, we present a new strong baseline for more consistent predictive confidence in deep models, called fitted ensembles, where overconfident predictions are rectified by transformed versions of the original classification task. Fitted ensembles can naturally detect OOD examples without requiring auxiliary data by observing contradicting predictions among its components. Experiments on MNIST, SVHN, CIFAR-10/100, and ImageNet show fitted ensemble significantly outperform conventional ensembles on OOD examples and are possible to scale.