1.What makes for good views for contrastive learning ⬇️
Contrastive learning between multiple views of the data has recently achieved state of the art performance in the field of self-supervised representation learning. Despite its success, the influence of different view choices has been less studied. In this paper, we use empirical analysis to better understand the importance of view selection, and argue that we should reduce the mutual information (MI) between views while keeping task-relevant information intact. To verify this hypothesis, we devise unsupervised and semi-supervised frameworks that learn effective views by aiming to reduce their MI. We also consider data augmentation as a way to reduce MI, and show that increasing data augmentation indeed leads to decreasing MI and improves downstream classification accuracy. As a by-product, we also achieve a new state-of-the-art accuracy on unsupervised pre-training for ImageNet classification (
$73%$ top-1 linear readoff with a ResNet-50). In addition, transferring our models to PASCAL VOC object detection and COCO instance segmentation consistently outperforms supervised pre-training. Code:this http URL
2.Intra- and Inter-Action Understanding via Temporal Action Parsing ⬇️
Current methods for action recognition primarily rely on deep convolutional networks to derive feature embeddings of visual and motion features. While these methods have demonstrated remarkable performance on standard benchmarks, we are still in need of a better understanding as to how the videos, in particular their internal structures, relate to high-level semantics, which may lead to benefits in multiple aspects, e.g. interpretable predictions and even new methods that can take the recognition performances to a next level. Towards this goal, we construct TAPOS, a new dataset developed on sport videos with manual annotations of sub-actions, and conduct a study on temporal action parsing on top. Our study shows that a sport activity usually consists of multiple sub-actions and that the awareness of such temporal structures is beneficial to action recognition. We also investigate a number of temporal parsing methods, and thereon devise an improved method that is capable of mining sub-actions from training data without knowing the labels of them. On the constructed TAPOS, the proposed method is shown to reveal intra-action information, i.e. how action instances are made of sub-actions, and inter-action information, i.e. one specific sub-action may commonly appear in various actions.
3.Compute-Bound and Low-Bandwidth Distributed 3D Graph-SLAM ⬇️
This article describes a new approach for distributed 3D SLAM map building. The key contribution of this article is the creation of a distributed graph-SLAM map-building architecture responsive to bandwidth and computational needs of the robotic platform. Responsiveness is afforded by the integration of a 3D point cloud to plane cloud compression algorithm that approximates dense 3D point cloud using local planar patches. Compute bound platforms may restrict the computational duration of the compression algorithm and low-bandwidth platforms can restrict the size of the compression result. The backbone of the approach is an ultra-fast adaptive 3D compression algorithm that transforms swaths of 3D planar surface data into planar patches attributed with image textures. Our approach uses DVO SLAM, a leading algorithm for 3D mapping, and extends it by computationally isolating map integration tasks from local Guidance, Navigation, and Control tasks and includes an addition of a network protocol to share the compressed plane clouds. The joint effect of these contributions allows agents with 3D sensing capabilities to calculate and communicate compressed map information commensurate with their onboard computational resources and communication channel capacities. This opens SLAM mapping to new categories of robotic platforms that may have computational and memory limits that prohibit other SLAM solutions.
4.Reducing Overlearning through Disentangled Representations by Suppressing Unknown Tasks ⬇️
Existing deep learning approaches for learning visual features tend to overlearn and extract more information than what is required for the task at hand. From a privacy preservation perspective, the input visual information is not protected from the model; enabling the model to become more intelligent than it is trained to be. Current approaches for suppressing additional task learning assume the presence of ground truth labels for the tasks to be suppressed during training time. In this research, we propose a three-fold novel contribution: (i) a model-agnostic solution for reducing model overlearning by suppressing all the unknown tasks, (ii) a novel metric to measure the trust score of a trained deep learning model, and (iii) a simulated benchmark dataset, PreserveTask, having five different fundamental image classification tasks to study the generalization nature of models. In the first set of experiments, we learn disentangled representations and suppress overlearning of five popular deep learning models: VGG16, VGG19, Inception-v1, MobileNet, and DenseNet on PreserverTask dataset. Additionally, we show results of our framework on color-MNIST dataset and practical applications of face attribute preservation in Diversity in Faces (DiF) and IMDB-Wiki dataset.
5.Discriminative Dictionary Design for Action Classification in Still Images and Videos ⬇️
In this paper, we address the problem of action recognition from still images and videos. Traditional local features such as SIFT, STIP etc. invariably pose two potential problems: 1) they are not evenly distributed in different entities of a given category and 2) many of such features are not exclusive of the visual concept the entities represent. In order to generate a dictionary taking the aforementioned issues into account, we propose a novel discriminative method for identifying robust and category specific local features which maximize the class separability to a greater extent. Specifically, we pose the selection of potent local descriptors as filtering based feature selection problem which ranks the local features per category based on a novel measure of distinctiveness. The underlying visual entities are subsequently represented based on the learned dictionary and this stage is followed by action classification using the random forest model followed by label propagation refinement. The framework is validated on the action recognition datasets based on still images (Stanford-40) as well as videos (UCF-50) and exhibits superior performances than the representative methods from the literature.
6.Classification of Industrial Control Systems screenshots using Transfer Learning ⬇️
Industrial Control Systems depend heavily on security and monitoring protocols. Several tools are available for this purpose, which scout vulnerabilities and take screenshots from various control panels for later analysis. However, they do not adequately classify images into specific control groups, which can difficult operations performed by manual operators. In order to solve this problem, we use transfer learning with five CNN architectures, pre-trained on Imagenet, to determine which one best classifies screenshots obtained from Industrial Controls Systems. Using 337 manually labeled images, we train these architectures and study their performance both in accuracy and CPU and GPU time. We find out that MobilenetV1 is the best architecture based on its 97,95% of F1-Score, and its speed on CPU with 0.47 seconds per image. In systems where time is critical and GPU is available, VGG16 is preferable because it takes 0.04 seconds to process images, but dropping performance to 87,67%.
7.Label Efficient Visual Abstractions for Autonomous Driving ⬇️
It is well known that semantic segmentation can be used as an effective intermediate representation for learning driving policies. However, the task of street scene semantic segmentation requires expensive annotations. Furthermore, segmentation algorithms are often trained irrespective of the actual driving task, using auxiliary image-space loss functions which are not guaranteed to maximize driving metrics such as safety or distance traveled per intervention. In this work, we seek to quantify the impact of reducing segmentation annotation costs on learned behavior cloning agents. We analyze several segmentation-based intermediate representations. We use these visual abstractions to systematically study the trade-off between annotation efficiency and driving performance, i.e., the types of classes labeled, the number of image samples used to learn the visual abstraction model, and their granularity (e.g., object masks vs. 2D bounding boxes). Our analysis uncovers several practical insights into how segmentation-based visual abstractions can be exploited in a more label efficient manner. Surprisingly, we find that state-of-the-art driving performance can be achieved with orders of magnitude reduction in annotation cost. Beyond label efficiency, we find several additional training benefits when leveraging visual abstractions, such as a significant reduction in the variance of the learned policy when compared to state-of-the-art end-to-end driving models.
8.Perceptual Hashing applied to Tor domains recognition ⬇️
The Tor darknet hosts different types of illegal content, which are monitored by cybersecurity agencies. However, manually classifying Tor content can be slow and error-prone. To support this task, we introduce Frequency-Dominant Neighborhood Structure (F-DNS), a new perceptual hashing method for automatically classifying domains by their screenshots. First, we evaluated F-DNS using images subject to various content preserving operations. We compared them with their original images, achieving better correlation coefficients than other state-of-the-art methods, especially in the case of rotation. Then, we applied F-DNS to categorize Tor domains using the Darknet Usage Service Images-2K (DUSI-2K), a dataset with screenshots of active Tor service domains. Finally, we measured the performance of F-DNS against an image classification approach and a state-of-the-art hashing method. Our proposal obtained 98.75% accuracy in Tor images, surpassing all other methods compared.
9.Classifying Suspicious Content in Tor Darknet ⬇️
One of the tasks of law enforcement agencies is to find evidence of criminal activity in the Darknet. However, visiting thousands of domains to locate visual information containing illegal acts manually requires a considerable amount of time and resources. Furthermore, the background of the images can pose a challenge when performing classification. To solve this problem, in this paper, we explore the automatic classification Tor Darknet images using Semantic Attention Keypoint Filtering, a strategy that filters non-significant features at a pixel level that do not belong to the object of interest, by combining saliency maps with Bag of Visual Words (BoVW). We evaluated SAKF on a custom Tor image dataset against CNN features: MobileNet v1 and Resnet50, and BoVW using dense SIFT descriptors, achieving a result of 87.98% accuracy and outperforming all other approaches.
10.Map Generation from Large Scale Incomplete and Inaccurate Data Labels ⬇️
Accurately and globally mapping human infrastructure is an important and challenging task with applications in routing, regulation compliance monitoring, and natural disaster response management etc.. In this paper we present progress in developing an algorithmic pipeline and distributed compute system that automates the process of map creation using high resolution aerial images. Unlike previous studies, most of which use datasets that are available only in a few cities across the world, we utilizes publicly available imagery and map data, both of which cover the contiguous United States (CONUS). We approach the technical challenge of inaccurate and incomplete training data adopting state-of-the-art convolutional neural network architectures such as the U-Net and the CycleGAN to incrementally generate maps with increasingly more accurate and more complete labels of man-made infrastructure such as roads and houses. Since scaling the mapping task to CONUS calls for parallelization, we then adopted an asynchronous distributed stochastic parallel gradient descent training scheme to distribute the computational workload onto a cluster of GPUs with nearly linear speed-up.
11.Deep learning with 4D spatio-temporal data representations for OCT-based force estimation ⬇️
Estimating the forces acting between instruments and tissue is a challenging problem for robot-assisted minimally-invasive surgery. Recently, numerous vision-based methods have been proposed to replace electro-mechanical approaches. Moreover, optical coherence tomography (OCT) and deep learning have been used for estimating forces based on deformation observed in volumetric image data. The method demonstrated the advantage of deep learning with 3D volumetric data over 2D depth images for force estimation. In this work, we extend the problem of deep learning-based force estimation to 4D spatio-temporal data with streams of 3D OCT volumes. For this purpose, we design and evaluate several methods extending spatio-temporal deep learning to 4D which is largely unexplored so far. Furthermore, we provide an in-depth analysis of multi-dimensional image data representations for force estimation, comparing our 4D approach to previous, lower-dimensional methods. Also, we analyze the effect of temporal information and we study the prediction of short-term future force values, which could facilitate safety features. For our 4D force estimation architectures, we find that efficient decoupling of spatial and temporal processing is advantageous. We show that using 4D spatio-temporal data outperforms all previously used data representations with a mean absolute error of 10.7mN. We find that temporal information is valuable for force estimation and we demonstrate the feasibility of force prediction.
12.Dynamic Refinement Network for Oriented and Densely Packed Object Detection ⬇️
Object detection has achieved remarkable progress in the past decade. However, the detection of oriented and densely packed objects remains challenging because of following inherent reasons: (1) receptive fields of neurons are all axis-aligned and of the same shape, whereas objects are usually of diverse shapes and align along various directions; (2) detection models are typically trained with generic knowledge and may not generalize well to handle specific objects at test time; (3) the limited dataset hinders the development on this task. To resolve the first two issues, we present a dynamic refinement network that consists of two novel components, i.e., a feature selection module (FSM) and a dynamic refinement head (DRH). Our FSM enables neurons to adjust receptive fields in accordance with the shapes and orientations of target objects, whereas the DRH empowers our model to refine the prediction dynamically in an object-aware manner. To address the limited availability of related benchmarks, we collect an extensive and fully annotated dataset, namely, SKU110K-R, which is relabeled with oriented bounding boxes based on SKU110K. We perform quantitative evaluations on several publicly available benchmarks including DOTA, HRSC2016, SKU110K, and our own SKU110K-R dataset. Experimental results show that our method achieves consistent and substantial gains compared with baseline approaches. The code and dataset are available at this https URL.
13.Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection ⬇️
This paper presents a novel 3D object detection framework that processes LiDAR data directly on a representation of the sensor's native range images. When operating in the range image view, one faces learning challenges, including occlusion and considerable scale variation, limiting the obtainable accuracy. To address these challenges, a range-conditioned dilated block (RCD) is proposed to dynamically adjust a continuous dilation rate as a function of the measured range, achieving scale invariance. Furthermore, soft range gating helps mitigate the effect of occlusion. An end-to-end trained box-refinement network brings additional performance improvements in occluded areas, and produces more accurate bounding box predictions. On the challenging Waymo Open Dataset, our improved range-based detector outperforms state of the art at long range detection. Our framework is superior to prior multiview, voxel-based methods over all ranges, setting a new baseline for range-based 3D detection on this large scale public dataset.
14.Rethinking Performance Estimation in Neural Architecture Search ⬇️
Neural architecture search (NAS) remains a challenging problem, which is attributed to the indispensable and time-consuming component of performance estimation (PE). In this paper, we provide a novel yet systematic rethinking of PE in a resource constrained regime, termed budgeted PE (BPE), which precisely and effectively estimates the performance of an architecture sampled from an architecture space. Since searching an optimal BPE is extremely time-consuming as it requires to train a large number of networks for evaluation, we propose a Minimum Importance Pruning (MIP) approach. Given a dataset and a BPE search space, MIP estimates the importance of hyper-parameters using random forest and subsequently prunes the minimum one from the next iteration. In this way, MIP effectively prunes less important hyper-parameters to allocate more computational resource on more important ones, thus achieving an effective exploration. By combining BPE with various search algorithms including reinforcement learning, evolution algorithm, random search, and differentiable architecture search, we achieve 1, 000x of NAS speed up with a negligible performance drop comparing to the SOTA
15.Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review ⬇️
Recently, the advancement of deep learning in discriminative feature learning from 3D LiDAR data has led to rapid development in the field of autonomous driving. However, automated processing uneven, unstructured, noisy, and massive 3D point clouds is a challenging and tedious task. In this paper, we provide a systematic review of existing compelling deep learning architectures applied in LiDAR point clouds, detailing for specific tasks in autonomous driving such as segmentation, detection, and classification. Although several published research papers focus on specific topics in computer vision for autonomous vehicles, to date, no general survey on deep learning applied in LiDAR point clouds for autonomous vehicles exists. Thus, the goal of this paper is to narrow the gap in this topic. More than 140 key contributions in the recent five years are summarized in this survey, including the milestone 3D deep architectures, the remarkable deep learning applications in 3D semantic segmentation, object detection, and classification; specific datasets, evaluation metrics, and the state of the art performance. Finally, we conclude the remaining challenges and future researches.
16.Relevant Region Prediction for Crowd Counting ⬇️
Crowd counting is a concerned and challenging task in computer vision. Existing density map based methods excessively focus on the individuals' localization which harms the crowd counting performance in highly congested scenes. In addition, the dependency between the regions of different density is also ignored. In this paper, we propose Relevant Region Prediction (RRP) for crowd counting, which consists of the Count Map and the Region Relation-Aware Module (RRAM). Each pixel in the count map represents the number of heads falling into the corresponding local area in the input image, which discards the detailed spatial information and forces the network pay more attention to counting rather than localizing individuals. Based on the Graph Convolutional Network (GCN), Region Relation-Aware Module is proposed to capture and exploit the important region dependency. The module builds a fully connected directed graph between the regions of different density where each node (region) is represented by weighted global pooled feature, and GCN is learned to map this region graph to a set of relation-aware regions representations. Experimental results on three datasets show that our method obviously outperforms other existing state-of-the-art methods.
17.Active Speakers in Context ⬇️
Current methods for active speak er detection focus on modeling short-term audiovisual information from a single speaker. Although this strategy can be enough for addressing single-speaker scenarios, it prevents accurate detection when the task is to identify who of many candidate speakers are talking. This paper introduces the Active Speaker Context, a novel representation that models relationships between multiple speakers over long time horizons. Our Active Speaker Context is designed to learn pairwise and temporal relations from an structured ensemble of audio-visual observations. Our experiments show that a structured feature ensemble already benefits the active speaker detection performance. Moreover, we find that the proposed Active Speaker Context improves the state-of-the-art on the AVA-ActiveSpeaker dataset achieving a mAP of 87.1%. We present ablation studies that verify that this result is a direct consequence of our long-term multi-speaker analysis.
18.On Evaluating Weakly Supervised Action Segmentation Methods ⬇️
Action segmentation is the task of temporally segmenting every frame of an untrimmed video. Weakly supervised approaches to action segmentation, especially from transcripts have been of considerable interest to the computer vision community. In this work, we focus on two aspects of the use and evaluation of weakly supervised action segmentation approaches that are often overlooked: the performance variance over multiple training runs and the impact of selecting feature extractors for this this http URL tackle the first problem, we train each method on the Breakfast dataset 5 times and provide average and standard deviation of the results. Our experiments show that the standard deviation over these repetitions is between 1 and 2.5% and significantly affects the comparison between different approaches. Furthermore, our investigation on feature extraction shows that, for the studied weakly-supervised action segmentation methods, higher-level I3D features perform worse than classical IDT features.
19.Ventral-Dorsal Neural Networks: Object Detection via Selective Attention ⬇️
Deep Convolutional Neural Networks (CNNs) have been repeatedly proven to perform well on image classification tasks. Object detection methods, however, are still in need of significant improvements. In this paper, we propose a new framework called Ventral-Dorsal Networks (VDNets) which is inspired by the structure of the human visual system. Roughly, the visual input signal is analyzed along two separate neural streams, one in the temporal lobe and the other in the parietal lobe. The coarse functional distinction between these streams is between object recognition -- the "what" of the signal -- and extracting location related information -- the "where" of the signal. The ventral pathway from primary visual cortex, entering the temporal lobe, is dominated by "what" information, while the dorsal pathway, into the parietal lobe, is dominated by "where" information. Inspired by this structure, we propose the integration of a "Ventral Network" and a "Dorsal Network", which are complementary. Information about object identity can guide localization, and location information can guide attention to relevant image regions, improving object recognition. This new dual network framework sharpens the focus of object detection. Our experimental results reveal that the proposed method outperforms state-of-the-art object detection approaches on PASCAL VOC 2007 by 8% (mAP) and PASCAL VOC 2012 by 3% (mAP). Moreover, a comparison of techniques on Yearbook images displays substantial qualitative and quantitative benefits of VDNet.
20.Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting ⬇️
Recently data-driven image inpainting methods have made inspiring progress, impacting fundamental image editing tasks such as object removal and damaged image repairing. These methods are more effective than classic approaches, however, due to memory limitations they can only handle low-resolution inputs, typically smaller than 1K. Meanwhile, the resolution of photos captured with mobile devices increases up to 8K. Naive up-sampling of the low-resolution inpainted result can merely yield a large yet blurry result. Whereas, adding a high-frequency residual image onto the large blurry image can generate a sharp result, rich in details and textures. Motivated by this, we propose a Contextual Residual Aggregation (CRA) mechanism that can produce high-frequency residuals for missing contents by weighted aggregating residuals from contextual patches, thus only requiring a low-resolution prediction from the network. Since convolutional layers of the neural network only need to operate on low-resolution inputs and outputs, the cost of memory and computing power is thus well suppressed. Moreover, the need for high-resolution training datasets is alleviated. In our experiments, we train the proposed model on small images with resolutions 512x512 and perform inference on high-resolution images, achieving compelling inpainting quality. Our model can inpaint images as large as 8K with considerable hole sizes, which is intractable with previous learning-based approaches. We further elaborate on the light-weight design of the network architecture, achieving real-time performance on 2K images on a GTX 1080 Ti GPU. Codes are available at: Atlas200dk/sample-imageinpainting-HiFill.
21.Representation Learning with Fine-grained Patterns ⬇️
With the development of computational power and techniques for data collection, deep learning demonstrates a superior performance over many existing algorithms on benchmark data sets. Many efforts have been devoted to studying the mechanism of deep learning. One of important observations is that deep learning can learn the discriminative patterns from raw materials directly in a task-dependent manner. It makes the patterns obtained by deep learning outperform hand-crafted features significantly. However, those patterns can be misled by the training task when the target task is different. In this work, we investigate a prevalent problem in real-world applications, where the training set only accesses to the supervised information from superclasses but the target task is defined on fine-grained classes. Each superclass can contain multiple fine-grained classes. In this scenario, fine-grained patterns are essential to classify examples from fine-grained classes while they can be neglected when training only with labels from superclasses. To mitigate the challenge, we propose the algorithm to explore the fine-grained patterns sufficiently without additional supervised information. Besides, our analysis indicates that the performance of learned patterns on the fine-grained classes can be theoretically guaranteed. Finally, an efficient algorithm is developed to reduce the cost of optimization. The experiments on real-world data sets verify that the propose algorithm can significantly improve the performance on the fine-grained classes with information from superclasses only.
22.Tensor completion via nonconvex tensor ring rank minimization with guaranteed convergence ⬇️
In recent studies, the tensor ring (TR) rank has shown high effectiveness in tensor completion due to its ability of capturing the intrinsic structure within high-order tensors. A recently proposed TR rank minimization method is based on the convex relaxation by penalizing the weighted sum of nuclear norm of TR unfolding matrices. However, this method treats each singular value equally and neglects their physical meanings, which usually leads to suboptimal solutions in practice. In this paper, we propose to use the logdet-based function as a nonconvex smooth relaxation of the TR rank for tensor completion, which can more accurately approximate the TR rank and better promote the low-rankness of the solution. To solve the proposed nonconvex model efficiently, we develop an alternating direction method of multipliers algorithm and theoretically prove that, under some mild assumptions, our algorithm converges to a stationary point. Extensive experiments on color images, multispectral images, and color videos demonstrate that the proposed method outperforms several state-of-the-art competitors in both visual and quantitative comparison. Key words: nonconvex optimization, tensor ring rank, logdet function, tensor completion, alternating direction method of multipliers.
23.An Innovative Approach to Determine Rebar Depth and Size by Comparing GPR Data with a Theoretical Database ⬇️
Ground penetrating radar (GPR) is an efficient technique used for rapidly recognizing embedded rebar in concrete structures. However, due to the difficulty in extracting signals from GPR data and the intrinsic coupling between the rebar depth and size showing in the data, simultaneously determining rebar depth and size is challenging. This paper proposes an innovative algorithm to address this issue. First, the hyperbola signal from the GPR data is identified by direct wave removal, signal reconstruction and separation. Subsequently, a database is developed from a series of theoretical hyperbolas and then compared with the extracted hyperbola outlines. Finally, the rebar depth and size are determined by searching for the closest counterpart in the database. The obtained results are very promising and indicate that: (1) implementing the method presented in this paper can completely remove the direct wave noise from the GPR data, and can successfully extract the outlines from the interlaced hyperbolas; and (2) the proposed method can simultaneously determine the rebar depth and size with the accuracy of 100% and 95.11%, respectively.
24.InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs ⬇️
Although Generative Adversarial Networks (GANs) have made significant progress in face synthesis, there lacks enough understanding of what GANs have learned in the latent representation to map a randomly sampled code to a photo-realistic face image. In this work, we propose a framework, called InterFaceGAN, to interpret the disentangled face representation learned by the state-of-the-art GAN models and thoroughly analyze the properties of the facial semantics in the latent space. We first find that GANs actually learn various semantics in some linear subspaces of the latent space when being trained to synthesize high-quality faces. After identifying the subspaces of the corresponding latent semantics, we are able to realistically manipulate the facial attributes occurring in the synthesized images without retraining the model. We then conduct a detailed study on the correlation between different semantics and manage to better disentangle them via subspace projection, resulting in more precise control of the attribute manipulation. Besides manipulating gender, age, expression, and the presence of eyeglasses, we can even alter the face pose as well as fix the artifacts accidentally generated by GANs. Furthermore, we perform in-depth face identity analysis and layer-wise analysis to quantitatively evaluate the editing results. Finally, we apply our approach to real face editing by involving GAN inversion approaches as well as explicitly training additional feed-forward models based on the synthetic data established by InterFaceGAN. Extensive experimental results suggest that learning to synthesize faces spontaneously brings a disentangled and controllable face representation.
25.Automated Copper Alloy Grain Size Evaluation Using a Deep-learning CNN ⬇️
Moog Inc. has automated the evaluation of copper (Cu) alloy grain size using a deep-learning convolutional neural network (CNN). The proof-of-concept automated image acquisition and batch-wise image processing offers the potential for significantly reduced labor, improved accuracy of grain evaluation, and decreased overall turnaround times for approving Cu alloy bar stock for use in flight critical aircraft hardware. A classification accuracy of 91.1% on individual sub-images of the Cu alloy coupons was achieved. Process development included minimizing the variation in acquired image color, brightness, and resolution to create a dataset with 12300 sub-images, and then optimizing the CNN hyperparameters on this dataset using statistical design of experiments (DoE).
Over the development of the automated Cu alloy grain size evaluation, a degree of "explainability" in the artificial intelligence (XAI) output was realized, based on the decomposition of the large raw images into many smaller dataset sub-images, through the ability to explain the CNN ensemble image output via inspection of the classification results from the individual smaller sub-images.
26.Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere ⬇️
Contrastive representation learning has been outstandingly successful in practice. In this work, we identify two key properties related to the contrastive loss: (1) alignment (closeness) of features from positive pairs, and (2) uniformity of the induced distribution of the (normalized) features on the hypersphere. We prove that, asymptotically, the contrastive loss optimizes these properties, and analyze their positive effects on downstream tasks. Empirically, we introduce an optimizable metric to quantify each property. Extensive experiments on standard vision and language datasets confirm the strong agreement between both metrics and downstream task performance. Remarkably, directly optimizing for these two metrics leads to representations with comparable or better performance at downstream tasks than contrastive learning.
Project Page: this https URL
Code: this https URL
27.Lung Segmentation from Chest X-rays using Variational Data Imputation ⬇️
Pulmonary opacification is the inflammation in the lungs caused by many respiratory ailments, including the novel corona virus disease 2019 (COVID-19). Chest X-rays (CXRs) with such opacifications render regions of lungs imperceptible, making it difficult to perform automated image analysis on them. In this work, we focus on segmenting lungs from such abnormal CXRs as part of a pipeline aimed at automated risk scoring of COVID-19 from CXRs. We treat the high opacity regions as missing data and present a modified CNN-based image segmentation network that utilizes a deep generative model for data imputation. We train this model on normal CXRs with extensive data augmentation and demonstrate the usefulness of this model to extend to cases with extreme abnormalities.
28.Data Consistent CT Reconstruction from Insufficient Data with Learned Prior Images ⬇️
Image reconstruction from insufficient data is common in computed tomography (CT), e.g., image reconstruction from truncated data, limited-angle data and sparse-view data. Deep learning has achieved impressive results in this field. However, the robustness of deep learning methods is still a concern for clinical applications due to the following two challenges: a) With limited access to sufficient training data, a learned deep learning model may not generalize well to unseen data; b) Deep learning models are sensitive to noise. Therefore, the quality of images processed by neural networks only may be inadequate. In this work, we investigate the robustness of deep learning in CT image reconstruction by showing false negative and false positive lesion cases. Since learning-based images with incorrect structures are likely not consistent with measured projection data, we propose a data consistent reconstruction (DCR) method to improve their image quality, which combines the advantages of compressed sensing and deep learning: First, a prior image is generated by deep learning. Afterwards, unmeasured projection data are inpainted by forward projection of the prior image. Finally, iterative reconstruction with reweighted total variation regularization is applied, integrating data consistency for measured data and learned prior information for missing data. The efficacy of the proposed method is demonstrated in cone-beam CT with truncated data, limited-angle data and sparse-view data, respectively. For example, for truncated data, DCR achieves a mean root-mean-square error of 24 HU and a mean structure similarity index of 0.999 inside the field-of-view for different patients in the noisy case, while the state-of-the-art U-Net method achieves 55 HU and 0.995 respectively for these two metrics.
29.A Modified Fourier-Mellin Approach for Source Device Identification on Stabilized Videos ⬇️
To decide whether a digital video has been captured by a given device, multimedia forensic tools usually exploit characteristic noise traces left by the camera sensor on the acquired frames. This analysis requires that the noise pattern characterizing the camera and the noise pattern extracted from video frames under analysis are geometrically aligned. However, in many practical scenarios this does not occur, thus a re-alignment or synchronization has to be performed. Current solutions often require time consuming search of the realignment transformation parameters. In this paper, we propose to overcome this limitation by searching scaling and rotation parameters in the frequency domain. The proposed algorithm tested on real videos from a well-known state-of-the-art dataset shows promising results.
30.AutoML Segmentation for 3D Medical Image Data: Contribution to the MSD Challenge 2018 ⬇️
Fueled by recent advances in machine learning, there has been tremendous progress in the field of semantic segmentation for the medical image computing community. However, developed algorithms are often optimized and validated by hand based on one task only. In combination with small datasets, interpreting the generalizability of the results is often difficult. The Medical Segmentation Decathlon challenge addresses this problem, and aims to facilitate development of generalizable 3D semantic segmentation algorithms that require no manual parametrization. Such an algorithm was developed and is presented in this paper. It consists of a 3D convolutional neural network with encoder-decoder architecture employing residual-connections, skip-connections and multi-level generation of predictions. It works on anisotropic voxel-geometries and has anisotropic depth, i.e., the number of downsampling steps is a task-specific parameter. These depths are automatically inferred for each task prior to training. By combining this flexible architecture with on-the-fly data augmentation and little-to-no pre-- or postprocessing, promising results could be achieved. The code developed for this challenge will be available online after the final deadline at: this https URL
31.Iterative Network for Image Super-Resolution ⬇️
Single image super-resolution (SISR), as a traditional ill-conditioned inverse problem, has been greatly revitalized by the recent development of convolutional neural networks (CNN). These CNN-based methods generally map a low-resolution image to its corresponding high-resolution version with sophisticated network structures and loss functions, showing impressive performances. This paper proposes a substantially different approach relying on the iterative optimization on HR space with an iterative super-resolution network (ISRN). We first analyze the observation model of image SR problem, inspiring a feasible solution by mimicking and fusing each iteration in a more general and efficient manner. Considering the drawbacks of batch normalization, we propose a feature normalization (FNorm) method to regulate the features in network. Furthermore, a novel block with F-Norm is developed to improve the network representation, termed as FNB. Residual-in-residual structure is proposed to form a very deep network, which groups FNBs with a long skip connection for better information delivery and stabling the training phase. Extensive experimental results on testing benchmarks with bicubic (BI) degradation show our ISRN can not only recover more structural information, but also achieve competitive or better PSNR/SSIM results with much fewer parameters compared to other works. Besides BI, we simulate the real-world degradation with blur-downscale (BD) and downscalenoise (DN). ISRN and its extension ISRN+ both achieve better performance than others with BD and DN degradation models.
32.Interactive exploration of population scale pharmacoepidemiology datasets ⬇️
Population-scale drug prescription data linked with adverse drug reaction (ADR) data supports the fitting of models large enough to detect drug use and ADR patterns that are not detectable using traditional methods on smaller datasets. However, detecting ADR patterns in large datasets requires tools for scalable data processing, machine learning for data analysis, and interactive visualization. To our knowledge no existing pharmacoepidemiology tool supports all three requirements. We have therefore created a tool for interactive exploration of patterns in prescription datasets with millions of samples. We use Spark to preprocess the data for machine learning and for analyses using SQL queries. We have implemented models in Keras and the scikit-learn framework. The model results are visualized and interpreted using live Python coding in Jupyter. We apply our tool to explore a 384 million prescription data set from the Norwegian Prescription Database combined with a 62 million prescriptions for elders that were hospitalized. We preprocess the data in two minutes, train models in seconds, and plot the results in milliseconds. Our results show the power of combining computational power, short computation times, and ease of use for analysis of population scale pharmacoepidemiology datasets. The code is open source and available at: this https URL
33.Attention-based network for low-light image enhancement ⬇️
The captured images under low light conditions often suffer insufficient brightness and notorious noise. Hence, low-light image enhancement is a key challenging task in computer vision. A variety of methods have been proposed for this task, but these methods often failed in an extreme low-light environment and amplified the underlying noise in the input image. To address such a difficult problem, this paper presents a novel attention-based neural network to generate high-quality enhanced low-light images from the raw sensor data. Specifically, we first employ attention strategy (i.e. channel attention and spatial attention modules) to suppress undesired chromatic aberration and noise. The channel attention module guides the network to refine redundant colour features. The spatial attention module focuses on denoising by taking advantage of the non-local correlation in the image. Furthermore, we propose a new pooling layer, called inverted shuffle layer, which adaptively selects useful information from previous features. Extensive experiments demonstrate the superiority of the proposed network in terms of suppressing the chromatic aberration and noise artifacts in enhancement, especially when the low-light image has severe noise.
34.FashionBERT: Text and Image Matching with Adaptive Loss for Cross-modal Retrieval ⬇️
In this paper, we address the text and image matching in cross-modal retrieval of the fashion industry. Different from the matching in the general domain, the fashion matching is required to pay much more attention to the fine-grained information in the fashion images and texts. Pioneer approaches detect the region of interests (i.e., RoIs) from images and use the RoI embeddings as image representations. In general, RoIs tend to represent the "object-level" information in the fashion images, while fashion texts are prone to describe more detailed information, e.g. styles, attributes. RoIs are thus not fine-grained enough for fashion text and image matching. To this end, we propose FashionBERT, which leverages patches as image features. With the pre-trained BERT model as the backbone network, FashionBERT learns high level representations of texts and images. Meanwhile, we propose an adaptive loss to trade off multitask learning in the FashionBERT modeling. Two tasks (i.e., text and image matching and cross-modal retrieval) are incorporated to evaluate FashionBERT. On the public dataset, experiments demonstrate FashionBERT achieves significant improvements in performances than the baseline and state-of-the-art approaches. In practice, FashionBERT is applied in a concrete cross-modal retrieval application. We provide the detailed matching performance and inference efficiency analysis.
35.Self-supervised Dynamic CT Perfusion Image Denoising with Deep Neural Networks ⬇️
Dynamic computed tomography perfusion (CTP) imaging is a promising approach for acute ischemic stroke diagnosis and evaluation. Hemodynamic parametric maps of cerebral parenchyma are calculated from repeated CT scans of the first pass of iodinated contrast through the brain. It is necessary to reduce the dose of CTP for routine applications due to the high radiation exposure from the repeated scans, where image denoising is necessary to achieve a reliable diagnosis. In this paper, we proposed a self-supervised deep learning method for CTP denoising, which did not require any high-dose reference images for training. The network was trained by mapping each frame of CTP to an estimation from its adjacent frames. Because the noise in the source and target was independent, this approach could effectively remove the noise. Being free from high-dose training images granted the proposed method easier adaptation to different scanning protocols. The method was validated on both simulation and a public real dataset. The proposed method achieved improved image quality compared to conventional denoising methods. On the real data, the proposed method also had improved spatial resolution and contrast-to-noise ratio compared to supervised learning which was trained on the simulation data
36.Inverse problems with second-order Total Generalized Variation constraints ⬇️
Total Generalized Variation (TGV) has recently been introduced as penalty functional for modelling images with edges as well as smooth variations. It can be interpreted as a "sparse" penalization of optimal balancing from the first up to the
$k$ -th distributional derivative and leads to desirable results when applied to image denoising, i.e.,$L^2$ -fitting with TGV penalty. The present paper studies TGV of second order in the context of solving ill-posed linear inverse problems. Existence and stability for solutions of Tikhonov-functional minimization with respect to the data is shown and applied to the problem of recovering an image from blurred and noisy data.
37.Webpage Segmentation for Extracting Images and Their Surrounding Contextual Information ⬇️
Web images come in hand with valuable contextual information. Although this information has long been mined for various uses such as image annotation, clustering of images, inference of image semantic content, etc., insufficient attention has been given to address issues in mining this contextual information. In this paper, we propose a webpage segmentation algorithm targeting the extraction of web images and their contextual information based on their characteristics as they appear on webpages. We conducted a user study to obtain a human-labeled dataset to validate the effectiveness of our method and experiments demonstrated that our method can achieve better results compared to an existing segmentation algorithm.