20200512.md

ArXiv cs.CV --Tue, 12 May 2020

1.Using Computer Vision to enhance Safety of Workforce in Manufacturing in a Post COVID World ⬇️

The COVID-19 pandemic forced governments across the world to impose lockdowns to prevent virus transmissions. This resulted in the shutdown of all economic activity and accordingly the production at manufacturing plants across most sectors was halted. While there is an urgency to resume production, there is an even greater need to ensure the safety of the workforce at the plant site. Reports indicate that maintaining social distancing and wearing face masks while at work clearly reduces the risk of transmission. We decided to use computer vision on CCTV feeds to monitor worker activity and detect violations which trigger real time voice alerts on the shop floor. This paper describes an efficient and economic approach of using AI to create a safe environment in a manufacturing setup. We demonstrate our approach to build a robust social distancing measurement algorithm using a mix of modern-day deep learning and classic projective geometry techniques. We have also described our face mask detection approach which provides a high accuracy across a range of customized masks.

2.Normalized Convolutional Neural Network ⬇️

In this paper, we propose Normalized Convolutional Neural Network(NCNN). NCNN is more fitted to a convolutional operator than other nomralizaiton methods. The normalized process is similar to a normalization methods, but NCNN is more adapative to sliced-inputs and corresponding the convolutional kernel. Therefor NCNN can be targeted to micro-batch training. Normalizaing of NC is conducted during convolutional process. In short, NC process is not usual normalization and can not be realized in deep learning framework optimizing standard convolution process. Hence we named this method 'Normalized Convolution'. As a result, NC process has universal property which means NC can be applied to any AI tasks involving convolution neural layer . Since NC don't need other normalization layer, NCNN looks like convolutional version of Self Normalizing Network.(SNN). Among micro-batch trainings, NCNN outperforms other batch-independent normalization methods. NCNN archives these superiority by standardizing rows of im2col matrix of inputs, which theoretically smooths the gradient of loss. The code need to manipulate standard convolution neural networks step by step. The code is available : this https URL NormalizedCNN.

3.Deep-Learning-based Automated Palm Tree Counting and Geolocation in Large Farms from Aerial Geotagged Images ⬇️

In this paper, we propose a deep learning framework for the automated counting and geolocation of palm trees from aerial images using convolutional neural networks. For this purpose, we collected aerial images in a palm tree Farm in the Kharj region, in Riyadh Saudi Arabia, using DJI drones, and we built a dataset of around 10,000 instances of palms trees. Then, we developed a convolutional neural network model using the state-of-the-art, Faster R-CNN algorithm. Furthermore, using the geotagged metadata of aerial images, we used photogrammetry concepts and distance corrections to detect the geographical location of detected palms trees automatically. This geolocation technique was tested on two different types of drones (DJI Mavic Pro, and Phantom 4 Pro), and was assessed to provide an average geolocation accuracy of 2.8m. This GPS tagging allows us to uniquely identify palm trees and count their number from a series of drone images, while correctly dealing with the issue of image overlapping. Moreover, it can be generalized to the geolocation of any other objects in UAV images.

4.On the Transferability of Winning Tickets in Non-Natural Image Datasets ⬇️

We study the generalization properties of pruned neural networks that are the winners of the lottery ticket hypothesis on datasets of natural images. We analyse their potential under conditions in which training data is scarce and comes from a non-natural domain. Specifically, we investigate whether pruned models that are found on the popular CIFAR-10/100 and Fashion-MNIST datasets, generalize to seven different datasets that come from the fields of digital pathology and digital heritage. Our results show that there are significant benefits in transferring and training sparse architectures over larger parametrized models, since in all of our experiments pruned networks, winners of the lottery ticket hypothesis, significantly outperform their larger unpruned counterparts. These results suggest that winning initializations do contain inductive biases that are generic to some extent, although, as reported by our experiments on the biomedical datasets, their generalization properties can be more limiting than what has been so far observed in the literature.

5.Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence ⬇️

This paper tackles the automatic colorization task of a sketch image given an already-colored reference image. Colorizing a sketch image is in high demand in comics, animation, and other content creation applications, but it suffers from information scarcity of a sketch image. To address this, a reference image can render the colorization process in a reliable and user-driven manner. However, it is difficult to prepare for a training data set that has a sufficient amount of semantically meaningful pairs of images as well as the ground truth for a colored image reflecting a given reference (e.g., coloring a sketch of an originally blue car given a reference green car). To tackle this challenge, we propose to utilize the identical image with geometric distortion as a virtual reference, which makes it possible to secure the ground truth for a colored output image. Furthermore, it naturally provides the ground truth for dense semantic correspondence, which we utilize in our internal attention mechanism for color transfer from reference to sketch input. We demonstrate the effectiveness of our approach in various types of sketch image colorization via quantitative as well as qualitative evaluation against existing methods.

6.Reference Pose Generation for Visual Localization via Learned Features and View Synthesis ⬇️

Visual Localization is one of the key enabling technologies for autonomous driving and augmented reality. High quality datasets with accurate 6 Degree-of-Freedom (DoF) reference poses are the foundation for benchmarking and improving existing methods. Traditionally, reference poses have been obtained via Structure-from-Motion (SfM). However, SfM itself relies on local features which are prone to fail when images were taken under different conditions, e.g., day/night changes. At the same time, manually annotating feature correspondences is not scalable and potentially inaccurate. In this work, we propose a semi-automated approach to generate reference poses based on feature matching between renderings of a 3D model and real images via learned features. Given an initial pose estimate, our approach iteratively refines the pose based on feature matches against a rendering of the model from the current pose estimate. We significantly improve the nighttime reference poses of the popular Aachen Day-Night dataset, showing that state-of-the-art visual localization methods perform better (up to 47%) than predicted by the original reference poses. We extend the dataset with new nighttime test images, provide uncertainty estimates for our new reference poses, and introduce a new evaluation criterion. We will make our reference poses and our framework publicly available upon publication.

7.FroDO: From Detections to 3D Objects ⬇️

Object-oriented maps are important for scene understanding since they jointly capture geometry and semantics, allow individual instantiation and meaningful reasoning about objects. We introduce FroDO, a method for accurate 3D reconstruction of object instances from RGB video that infers object location, pose and shape in a coarse-to-fine manner. Key to FroDO is to embed object shapes in a novel learnt space that allows seamless switching between sparse point cloud and dense DeepSDF decoding. Given an input sequence of localized RGB frames, FroDO first aggregates 2D detections to instantiate a category-aware 3D bounding box per object. A shape code is regressed using an encoder network before optimizing shape and pose further under the learnt shape priors using sparse and dense shape representations. The optimization uses multi-view geometric, photometric and silhouette losses. We evaluate on real-world datasets, including Pix3D, Redwood-OS, and ScanNet, for single-view, multi-view, and multi-object reconstruction.

8.Fine-Grained Visual Classification with Efficient End-to-end Localization ⬇️

The term fine-grained visual classification (FGVC) refers to classification tasks where the classes are very similar and the classification model needs to be able to find subtle differences to make the correct prediction. State-of-the-art approaches often include a localization step designed to help a classification network by localizing the relevant parts of the input images. However, this usually requires multiple iterations or passes through a full classification network or complex training schedules. In this work we present an efficient localization module that can be fused with a classification network in an end-to-end setup. On the one hand the module is trained by the gradient flowing back from the classification network. On the other hand, two self-supervised loss functions are introduced to increase the localization accuracy. We evaluate the new model on the three benchmark datasets CUB200-2011, Stanford Cars and FGVC-Aircraft and are able to achieve competitive recognition performance.

9.HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment ⬇️

Existing face restoration researches typically relies on either the degradation prior or explicit guidance labels for training, which often results in limited generalization ability over real-world images with heterogeneous degradations and rich background contents. In this paper, we investigate the more challenging and practical "dual-blind" version of the problem by lifting the requirements on both types of prior, termed as "Face Renovation"(FR). Specifically, we formulated FR as a semantic-guided generation problem and tackle it with a collaborative suppression and replenishment (CSR) approach. This leads to HiFaceGAN, a multi-stage framework containing several nested CSR units that progressively replenish facial details based on the hierarchical semantic guidance extracted from the front-end content-adaptive suppression modules. Extensive experiments on both synthetic and real face images have verified the superior performance of HiFaceGAN over a wide range of challenging restoration subtasks, demonstrating its versatility, robustness and generalization ability towards real-world face processing applications.

10.Quantitative Analysis of Image Classification Techniques for Memory-Constrained Devices ⬇️

Convolutional Neural Networks, or CNNs, are undoubtedly the state of the art for image classification. However, they typically come with the cost of a large memory footprint. Recently, there has been significant progress in the field of image classification on memory-constrained devices, such as Arduino Unos, with novel contributions like the ProtoNN, Bonsai and FastGRNN models. These methods have been shown to perform excellently on tasks such as speech recognition or optical character recognition using MNIST, but their potential on more complex, multi-channel and multi-class image classification has yet to be determined. This paper presents a comprehensive analysis that shows that even in memory-constrained environments, CNNs implemented memory-optimally using Direct Convolutions outperform ProtoNN, Bonsai and FastGRNN models on 3-channel image classification using CIFAR-10. For our analysis, we propose new methods of adjusting the FastGRNN model to work with multi-channel images and then evaluate each algorithm with a memory size budget of 8KB, 16KB, 32KB, 64KB and 128KB to show quantitatively that CNNs are still state-of-the-art in image classification, even when memory size is constrained.

11.Prototypical Contrastive Learning of Unsupervised Representations ⬇️

This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of the popular instance-wise contrastive learning. PCL implicitly encodes semantic structures of the data into the learned embedding space, and prevents the network from solely relying on low-level cues for solving unsupervised learning tasks. Specifically, we introduce prototypes as latent variables to help find the maximum-likelihood estimation of the network parameters in an Expectation-Maximization framework. We iteratively perform E-step as finding the distribution of prototypes via clustering and M-step as optimizing the network via contrastive learning. We propose ProtoNCE loss, a generalized version of the InfoNCE loss for contrastive learning by encouraging representations to be closer to their assigned prototypes. PCL achieves state-of-the-art results on multiple unsupervised representation learning benchmarks, with >10% accuracy improvement in low-resource transfer tasks.

12.Fake Face Detection via Adaptive Residuals Extraction Network ⬇️

With the proliferation of face image manipulation (FIM) techniques such as Face2Face and Deepfake, more fake face images are spreading over the internet, which brings serious challenges to public confidence. Face image forgery detection has made considerable progresses in exposing specific FIM, but it is still in scarcity of a robust fake face detector to expose face image forgeries under complex scenarios. Due to the relatively fixed structure, convolutional neural network (CNN) tends to learn image content representations. However, CNN should learn subtle tampering artifacts for image forensics tasks. We propose an adaptive residuals extraction network (AREN), which serves as pre-processing to suppress image content and highlight tampering artifacts. AREN exploits an adaptive convolution layer to predict image residuals, which are reused in subsequent layers to maximize manipulation artifacts by updating weights during the back-propagation pass. A fake face detector, namely ARENnet, is constructed by integrating AREN with CNN. Experimental results prove that the proposed AREN achieves desirable pre-processing. When detecting fake face images generated by various FIM techniques, ARENnet achieves an average accuracy up to 98.52%, which outperforms the state-of-the-art works. When detecting face images with unknown post-processing operations, the detector also achieves an average accuracy of 95.17%.

13.Conditional Image Generation and Manipulation for User-Specified Content ⬇️

In recent years, Generative Adversarial Networks (GANs) have improved steadily towards generating increasingly impressive real-world images. It is useful to steer the image generation process for purposes such as content creation. This can be done by conditioning the model on additional information. However, when conditioning on additional information, there still exists a large set of images that agree with a particular conditioning. This makes it unlikely that the generated image is exactly as envisioned by a user, which is problematic for practical content creation scenarios such as generating facial composites or stock photos. To solve this problem, we propose a single pipeline for text-to-image generation and manipulation. In the first part of our pipeline we introduce textStyleGAN, a model that is conditioned on text. In the second part of our pipeline we make use of the pre-trained weights of textStyleGAN to perform semantic facial image manipulation. The approach works by finding semantic directions in latent space. We show that this method can be used to manipulate facial images for a wide range of attributes. Finally, we introduce the CelebTD-HQ dataset, an extension to CelebA-HQ, consisting of faces and corresponding textual descriptions.

14.An Inductive Transfer Learning Approach using Cycle-consistent Adversarial Domain Adaptation with Application to Brain Tumor Segmentation ⬇️

With recent advances in supervised machine learning for medical image analysis applications, the annotated medical image datasets of various domains are being shared extensively. Given that the annotation labelling requires medical expertise, such labels should be applied to as many learning tasks as possible. However, the multi-modal nature of each annotated image renders it difficult to share the annotation label among diverse tasks. In this work, we provide an inductive transfer learning (ITL) approach to adopt the annotation label of the source domain datasets to tasks of the target domain datasets using Cycle-GAN based unsupervised domain adaptation (UDA). To evaluate the applicability of the ITL approach, we adopted the brain tissue annotation label on the source domain dataset of Magnetic Resonance Imaging (MRI) images to the task of brain tumor segmentation on the target domain dataset of MRI. The results confirm that the segmentation accuracy of brain tumor segmentation improved significantly. The proposed ITL approach can make significant contribution to the field of medical image analysis, as we develop a fundamental tool to improve and promote various tasks using medical images.

15.Celeganser: Automated Analysis of Nematode Morphology and Age ⬇️

The nematode Caenorhabditis elegans (C. elegans) serves as an important model organism in a wide variety of biological studies. In this paper we introduce a pipeline for automated analysis of C. elegans imagery for the purpose of studying life-span, health-span and the underlying genetic determinants of aging. Our system detects and segments the worm, and predicts body coordinates at each pixel location inside the worm. These coordinates provide dense correspondence across individual animals to allow for meaningful comparative analysis. We show that a model pre-trained to perform body-coordinate regression extracts rich features that can be used to predict the age of individual worms with high accuracy. This lays the ground for future research in quantifying the relation between organs' physiologic and biochemical state, and individual life/health-span.

16.Scope Head for Accurate Localization in Object Detection ⬇️

Existing anchor-based and anchor-free object detectors in multi-stage or one-stage pipelines have achieved very promising detection performance. However, they still encounter the design difficulty in hand-crafted 2D anchor definition and the learning complexity in 1D direct location regression. To tackle these issues, in this paper, we propose a novel detector coined as ScopeNet, which models anchors of each location as a mutually dependent relationship. This approach quantizes the prediction space and employs a coarse-to-fine strategy for localization. It achieves superior flexibility as in the regression based anchor-free methods, while produces more precise prediction. Besides, an inherit anchor selection score is learned to indicate the localization quality of the detection result, and we propose to better represent the confidence of a detection box by combining the category-classification score and the anchor-selection score. With our concise and effective design, the proposed ScopeNet achieves state-of-the-art results on COCO

17.Non-iterative Simultaneous Rigid Registration Method for Serial Sections of Biological Tissue ⬇️

In this paper, we propose a novel non-iterative algorithm to simultaneously estimate optimal rigid transformation for serial section images, which is a key component in volume reconstruction of serial sections of biological tissue. In order to avoid error accumulation and propagation caused by current algorithms, we add extra condition that the position of the first and the last section images should remain unchanged. This constrained simultaneous registration problem has not been solved before. Our algorithm method is non-iterative, it can simultaneously compute rigid transformation for a large number of serial section images in a short time. We prove that our algorithm gets optimal solution under ideal condition. And we test our algorithm with synthetic data and real data to verify our algorithm's effectiveness.

18.Learning Descriptors Invariance Through Equivalence Relations Within Manifold: A New Approach to Expression Invariant 3D Face Recognition ⬇️

This paper presents a unique approach for the dichotomy between useful and adverse variations of key-point descriptors, namely the identity and the expression variations in the descriptor (feature) space. The descriptors variations are learned from training examples. Based on the labels of the training data, the equivalence relations among the descriptors are established. Both types of descriptor variations are represented by a graph embedded in the descriptor manifold. The invariant recognition is then conducted as a graph search problem. A heuristic graph search algorithm suitable for the recognition under this setup was devised. The proposed approach was tests on the FRGC v2.0, the Bosphorus and the 3D TEC datasets. It has shown to enhance the recognition performance, under expression variations in particular, by considerable margins.

19.The Visual Social Distancing Problem ⬇️

One of the main and most effective measures to contain the recent viral outbreak is the maintenance of the so-called Social Distancing (SD). To comply with this constraint, workplaces, public institutions, transports and schools will likely adopt restrictions over the minimum inter-personal distance between people. Given this actual scenario, it is crucial to massively measure the compliance to such physical constraint in our life, in order to figure out the reasons of the possible breaks of such distance limitations, and understand if this implies a possible threat given the scene context. All of this, complying with privacy policies and making the measurement acceptable. To this end, we introduce the Visual Social Distancing (VSD) problem, defined as the automatic estimation of the inter-personal distance from an image, and the characterization of the related people aggregations. VSD is pivotal for a non-invasive analysis to whether people comply with the SD restriction, and to provide statistics about the level of safety of specific areas whenever this constraint is violated. We then discuss how VSD relates with previous literature in Social Signal Processing and indicate which existing Computer Vision methods can be used to manage such problem. We conclude with future challenges related to the effectiveness of VSD systems, ethical implications and future application scenarios.

20.A numerical method to estimate uncertainty in non-rigid structure from motion ⬇️

Semi-Definite Programming (SDP) with low-rank prior has been widely applied in Non-Rigid Structure from Motion (NRSfM). Based on a low-rank constraint, it avoids the inherent ambiguity of basis number selection in conventional base-shape or base-trajectory methods. Despite the efficiency in deformable shape reconstruction, it remains unclear how to assess the uncertainty of the recovered shape from the SDP process. In this paper, we present a statistical inference on the element-wise uncertainty quantification of the estimated deforming 3D shape points in the case of the exact low-rank SDP problem. A closed-form uncertainty quantification method is proposed and tested. Moreover, we extend the exact low-rank uncertainty quantification to the approximate low-rank scenario with a numerical optimal rank selection method, which enables solving practical application in SDP based NRSfM scenario. The proposed method provides an independent module to the SDP method and only requires the statistic information of the input 2D tracked points. Extensive experiments prove that the output 3D points have identical normal distribution to the 2D trackings, the proposed method and quantify the uncertainty accurately, and supports that it has desirable effects on routinely SDP low-rank based NRSfM solver.

21.Photometric Multi-View Mesh Refinement for High-Resolution Satellite Images ⬇️

Modern high-resolution satellite sensors collect optical imagery with ground sampling distances (GSDs) of 30-50cm, which has sparked a renewed interest in photogrammetric 3D surface reconstruction from satellite data. State-of-the-art reconstruction methods typically generate 2.5D elevation data. Here, we present an approach to recover full 3D surface meshes from multi-view satellite imagery. The proposed method takes as input a coarse initial mesh and refines it by iteratively updating all vertex positions to maximize the photo-consistency between images. Photo-consistency is measured in image space, by transferring texture from one image to another via the surface. We derive the equations to propagate changes in texture similarity through the rational function model (RFM), often also referred to as rational polynomial coefficient (RPC) model. Furthermore, we devise a hierarchical scheme to optimize the surface with gradient descent. In experiments with two different datasets, we show that the refinement improves the initial digital elevation models (DEMs) generated with conventional dense image matching. Moreover, we demonstrate that our method is able to reconstruct true 3D geometry, such as facade structures, if off-nadir views are available.

22.A Simple Semi-Supervised Learning Framework for Object Detection ⬇️

Semi-supervised learning (SSL) has promising potential for improving the predictive performance of machine learning models using unlabeled data. There has been remarkable progress, but the scope of demonstration in SSL has been limited to image classification tasks. In this paper, we propose STAC, a simple yet effective SSL framework for visual object detection along with a data augmentation strategy. STAC deploys highly confident pseudo labels of localized objects from an unlabeled image and updates the model by enforcing consistency via strong augmentations. We propose new experimental protocols to evaluate performance of semi-supervised object detection using MS-COCO and demonstrate the efficacy of STAC on both MS-COCO and VOC07. On VOC07, STAC improves the AP$^{0.5}$ from 76.30 to 79.08; on MS-COCO, STAC demonstrates 2x higher data efficiency by achieving 24.38 mAP using only 5% labeled data than supervised baseline that marks 23.86% using 10% labeled data. The code is available at \url{this https URL}.

23.A Generalized Kernel Risk Sensitive Loss for Robust Two-Dimensional Singular Value Decomposition ⬇️

Two-dimensional singular decomposition (2DSVD) has been widely used for image processing tasks, such as image reconstruction, classification, and clustering. However, traditional 2DSVD algorithm is based on the mean square error (MSE) loss, which is sensitive to outliers. To overcome this problem, we propose a robust 2DSVD framework based on a generalized kernel risk sensitive loss (GKRSL-2DSVD) which is more robust to noise and and outliers. Since the proposed objective function is non-convex, a majorization-minimization algorithm is developed to efficiently solve it with guaranteed convergence. The proposed framework has inherent properties of processing non-centered data, rotational invariant, being easily extended to higher order spaces. Experimental results on public databases demonstrate that the performance of the proposed method on different applications significantly outperforms that of all the benchmarks.

24.Domain Adaptation for Image Dehazing ⬇️

Image dehazing using learning-based methods has achieved state-of-the-art performance in recent years. However, most existing methods train a dehazing model on synthetic hazy images, which are less able to generalize well to real hazy images due to domain shift. To address this issue, we propose a domain adaptation paradigm, which consists of an image translation module and two image dehazing modules. Specifically, we first apply a bidirectional translation network to bridge the gap between the synthetic and real domains by translating images from one domain to another. And then, we use images before and after translation to train the proposed two image dehazing networks with a consistency constraint. In this phase, we incorporate the real hazy image into the dehazing training via exploiting the properties of the clear image (e.g., dark channel prior and image gradient smoothing) to further improve the domain adaptivity. By training image translation and dehazing network in an end-to-end manner, we can obtain better effects of both image translation and dehazing. Experimental results on both synthetic and real-world images demonstrate that our model performs favorably against the state-of-the-art dehazing algorithms.

25.A Simple and Scalable Shape Representation for 3D Reconstruction ⬇️

Deep learning applied to the reconstruction of 3D shapes has seen growing interest. A popular approach to 3D reconstruction and generation in recent years has been the CNN encoder-decoder model usually applied in voxel space. However, this often scales very poorly with the resolution limiting the effectiveness of these models. Several sophisticated alternatives for decoding to 3D shapes have been proposed typically relying on complex deep learning architectures for the decoder model. In this work, we show that this additional complexity is not necessary, and that we can actually obtain high quality 3D reconstruction using a linear decoder, obtained from principal component analysis on the signed distance function (SDF) of the surface. This approach allows easily scaling to larger resolutions. We show in multiple experiments that our approach is competitive with state-of-the-art methods. It also allows the decoder to be fine-tuned on the target task using a loss designed specifically for SDF transforms, obtaining further gains.

26.A Comparison of Few-Shot Learning Methods for Underwater Optical and Sonar Image Classification ⬇️

Deep convolutional neural networks have shown to perform well in underwater object recognition tasks, on both optical and sonar images. However, many such methods require hundreds, if not thousands, of images per class to generalize well to unseen examples. This is restricting in situations where obtaining and labeling larger volumes of data is impractical, such as observing a rare object, performing real-time operations, or operating in new underwater environments. Finding an algorithm capable of learning from only a few samples could reduce the time spent obtaining and labeling datasets, and accelerate the training of deep-learning models. To the best of our knowledge, this is the first paper to evaluate and compare several Few-Shot Learning (FSL) methods using underwater optical and side-scan sonar imagery. Our results show that FSL methods offer a significant advantage over the traditional transfer learning methods that employ fine-tuning of pre-trained models. Our findings show that FSL methods are not too far from being used on real-world robotics scenarios and expanding the capabilities of autonomous underwater systems.

27.A Unified Weight Learning and Low-Rank Regression Model for Robust Face Recognition ⬇️

Regression-based error modelling has been extensively studied for face recognition in recent years. The most important problem in regression-based error model is fitting the complex representation error caused by various corruptions and environment changes. However, existing works are not robust enough to model the complex corrupted errors. In this paper, we address this problem by a unified sparse weight learning and low-rank approximation regression model and applied it to the robust face recognition in the presence of varying types and levels of corruptions, such as random pixel corruptions and block occlusions, or disguise. The proposed model enables the random noise and contiguous occlusions to be addressed simultaneously. For the random noise, we proposed a generalized correntropy (GC) function to match the error distribution. For the structured error caused by occlusion or disguise, we proposed a GC function based rank approximation to measure the rank of error matrix. An effective iterative optimization is developed to solve the optimal weight learning and low-rank approximation. Extensive experimental results on three public face databases show that the proposed model can fit the error distribution and structure very well, thus obtain better recognition accuracy in comparison with the existing methods.

28.MOMBAT: Heart Rate Monitoring from Face Video using Pulse Modeling and Bayesian Tracking ⬇️

A non-invasive yet inexpensive method for heart rate (HR) monitoring is of great importance in many real-world applications including healthcare, psychology understanding, affective computing and biometrics. Face videos are currently utilized for such HR monitoring, but unfortunately this can lead to errors due to the noise introduced by facial expressions, out-of-plane movements, camera parameters (like focus change) and environmental factors. We alleviate these issues by proposing a novel face video based HR monitoring method MOMBAT, that is, MOnitoring using Modeling and BAyesian Tracking. We utilize out-of-plane face movements to define a novel quality estimation mechanism. Subsequently, we introduce a Fourier basis based modeling to reconstruct the cardiovascular pulse signal at the locations containing the poor quality, that is, the locations affected by out-of-plane face movements. Furthermore, we design a Bayesian decision theory based HR tracking mechanism to rectify the spurious HR estimates. Experimental results reveal that our proposed method, MOMBAT outperforms state-of-the-art HR monitoring methods and performs HR monitoring with an average absolute error of 1.329 beats per minute and the Pearson correlation between estimated and actual heart rate is 0.9746. Moreover, it demonstrates that HR monitoring is significantly

29.Variational Clustering: Leveraging Variational Autoencoders for Image Clustering ⬇️

Recent advances in deep learning have shown their ability to learn strong feature representations for images. The task of image clustering naturally requires good feature representations to capture the distribution of the data and subsequently differentiate data points from one another. Often these two aspects are dealt with independently and thus traditional feature learning alone does not suffice in partitioning the data meaningfully. Variational Autoencoders (VAEs) naturally lend themselves to learning data distributions in a latent space. Since we wish to efficiently discriminate between different clusters in the data, we propose a method based on VAEs where we use a Gaussian Mixture prior to help cluster the images accurately. We jointly learn the parameters of both the prior and the posterior distributions. Our method represents a true Gaussian Mixture VAE. This way, our method simultaneously learns a prior that captures the latent distribution of the images and a posterior to help discriminate well between data points. We also propose a novel reparametrization of the latent space consisting of a mixture of discrete and continuous variables. One key takeaway is that our method generalizes better across different datasets without using any pre-training or learnt models, unlike existing methods, allowing it to be trained from scratch in an end-to-end manner. We verify our efficacy and generalizability experimentally by achieving state-of-the-art results among unsupervised methods on a variety of datasets. To the best of our knowledge, we are the first to pursue image clustering using VAEs in a purely unsupervised manner on real image datasets.

30.Robust Tensor Decomposition for Image Representation Based on Generalized Correntropy ⬇️

Traditional tensor decomposition methods, e.g., two dimensional principal component analysis and two dimensional singular value decomposition, that minimize mean square errors, are sensitive to outliers. To overcome this problem, in this paper we propose a new robust tensor decomposition method using generalized correntropy criterion (Corr-Tensor). A Lagrange multiplier method is used to effectively optimize the generalized correntropy objective function in an iterative manner. The Corr-Tensor can effectively improve the robustness of tensor decomposition with the existence of outliers without introducing any extra computational cost. Experimental results demonstrated that the proposed method significantly reduces the reconstruction error on face reconstruction and improves the accuracies on handwritten digit recognition and facial image clustering.

31.Class-Aware Domain Adaptation for Improving Adversarial Robustness ⬇️

Recent works have demonstrated convolutional neural networks are vulnerable to adversarial examples, i.e., inputs to machine learning models that an attacker has intentionally designed to cause the models to make a mistake. To improve the adversarial robustness of neural networks, adversarial training has been proposed to train networks by injecting adversarial examples into the training data. However, adversarial training could overfit to a specific type of adversarial attack and also lead to standard accuracy drop on clean images. To this end, we propose a novel Class-Aware Domain Adaptation (CADA) method for adversarial defense without directly applying adversarial training. Specifically, we propose to learn domain-invariant features for adversarial examples and clean images via a domain discriminator. Furthermore, we introduce a class-aware component into the discriminator to increase the discriminative power of the network for adversarial examples. We evaluate our newly proposed approach using multiple benchmark datasets. The results demonstrate that our method can significantly improve the state-of-the-art of adversarial robustness for various attacks and maintain high performances on clean images.

32.Compact Neural Representation Using Attentive Network Pruning ⬇️

Deep neural networks have evolved to become power demanding and consequently difficult to apply to small-size mobile platforms. Network parameter reduction methods have been introduced to systematically deal with the computational and memory complexity of deep networks. We propose to examine the ability of attentive connection pruning to deal with redundancy reduction in neural networks as a contribution to the reduction of computational demand. In this work, we describe a Top-Down attention mechanism that is added to a Bottom-Up feedforward network to select important connections and subsequently prune redundant ones at all parametric layers. Our method not only introduces a novel hierarchical selection mechanism as the basis of pruning but also remains competitive with previous baseline methods in the experimental evaluation. We conduct experiments using different network architectures on popular benchmark datasets to show high compression ratio is achievable with negligible loss of accuracy.

33.Epipolar Transformers ⬇️

A common approach to localize 3D human joints in a synchronized and calibrated multi-view setup consists of two-steps: (1) apply a 2D detector separately on each view to localize joints in 2D, and (2) perform robust triangulation on 2D detections from each view to acquire the 3D joint locations. However, in step 1, the 2D detector is limited to solving challenging cases which could potentially be better resolved in 3D, such as occlusions and oblique viewing angles, purely in 2D without leveraging any 3D information. Therefore, we propose the differentiable "epipolar transformer", which enables the 2D detector to leverage 3D-aware features to improve 2D pose estimation. The intuition is: given a 2D location p in the current view, we would like to first find its corresponding point p' in a neighboring view, and then combine the features at p' with the features at p, thus leading to a 3D-aware feature at p. Inspired by stereo matching, the epipolar transformer leverages epipolar constraints and feature matching to approximate the features at p'. Experiments on InterHand and Human3.6M show that our approach has consistent improvements over the baselines. Specifically, in the condition where no external data is used, our Human3.6M model trained with ResNet-50 backbone and image size 256 x 256 outperforms state-of-the-art by 4.23 mm and achieves MPJPE 26.9 mm.

34.A Robust Matching Pursuit Algorithm Using Information Theoretic Learning ⬇️

Current orthogonal matching pursuit (OMP) algorithms calculate the correlation between two vectors using the inner product operation and minimize the mean square error, which are both suboptimal when there are non-Gaussian noises or outliers in the observation data. To overcome these problems, a new OMP algorithm is developed based on the information theoretic learning (ITL), which is built on the following new techniques: (1) an ITL-based correlation (ITL-Correlation) is developed as a new similarity measure which can better exploit higher-order statistics of the data, and is robust against many different types of noise and outliers in a sparse representation framework; (2) a non-second order statistic measurement and minimization method is developed to improve the robustness of OMP by overcoming the limitation of Gaussianity inherent in cost function based on second-order moments. The experimental results on both simulated and real-world data consistently demonstrate the superiority of the proposed OMP algorithm in data recovery, image reconstruction, and classification.

35.Generative Model-driven Structure Aligning Discriminative Embeddings for Transductive Zero-shot Learning ⬇️

Zero-shot Learning (ZSL) is a transfer learning technique which aims at transferring knowledge from seen classes to unseen classes. This knowledge transfer is possible because of underlying semantic space which is common to seen and unseen classes. Most existing approaches learn a projection function using labelled seen class data which maps visual data to semantic data. In this work, we propose a shallow but effective neural network-based model for learning such a projection function which aligns the visual and semantic data in the latent space while simultaneously making the latent space embeddings discriminative. As the above projection function is learned using the seen class data, the so-called projection domain shift exists. We propose a transductive approach to reduce the effect of domain shift, where we utilize unlabeled visual data from unseen classes to generate corresponding semantic features for unseen class visual samples. While these semantic features are initially generated using a conditional variational auto-encoder, they are used along with the seen class data to improve the projection function. We experiment on both inductive and transductive setting of ZSL and generalized ZSL and show superior performance on standard benchmark datasets AWA1, AWA2, CUB, SUN, FLO, and APY. We also show the efficacy of our model in the case of extremely less labelled data regime on different datasets in the context of ZSL.

36.Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events ⬇️

Along with the development of the modern smart city, human-centric video analysis is encountering the challenge of diverse and complex events in real scenes. A complex event relates to dense crowds, anomalous individual, or collective behavior. However, limited by the scale of available surveillance video datasets, few existing human analysis approaches report their performances on such complex events. To this end, we present a new large-scale dataset, named Human-in-Events or HiEve (human-centric video analysis in complex events), for understanding human motions, poses, and actions in a variety of realistic events, especially crowd & complex events. It contains a record number of poses (>1M), the largest number of action labels (>56k) for complex events, and one of the largest number of trajectories lasting for long terms (with average trajectory length >480). Besides, an online evaluation server is built for researchers to evaluate their approaches. Furthermore, we conduct extensive experiments on recent video analysis approaches, demonstrating that the HiEve is a challenging dataset for human-centric video analysis. We expect that the dataset will advance the development of cutting-edge techniques in human-centric analysis and the understanding of complex events. The dataset is available at this http URL .

37.Visually Impaired Aid using Convolutional Neural Networks, Transfer Learning, and Particle Competition and Cooperation ⬇️

Navigation and mobility are some of the major problems faced by visually impaired people in their daily lives. Advances in computer vision led to the proposal of some navigation systems. However, most of them require expensive and/or heavy hardware. In this paper we propose the use of convolutional neural networks (CNN), transfer learning, and semi-supervised learning (SSL) to build a framework aimed at the visually impaired aid. It has low computational costs and, therefore, may be implemented on current smartphones, without relying on any additional equipment. The smartphone camera can be used to automatically take pictures of the path ahead. Then, they will be immediately classified, providing almost instantaneous feedback to the user. We also propose a dataset to train the classifiers, including indoor and outdoor situations with different types of light, floor, and obstacles. Many different CNN architectures are evaluated as feature extractors and classifiers, by fine-tuning weights pre-trained on a much larger dataset. The graph-based SSL method, known as particle competition and cooperation, is also used for classification, allowing feedback from the user to be incorporated without retraining the underlying network. 92% and 80% classification accuracy is achieved in the proposed dataset in the best supervised and SSL scenarios, respectively.

38.Vehicle Re-Identification Based on Complementary Features ⬇️

In this work, we present our solution to the vehicle re-identification (vehicle Re-ID) track in AI City Challenge 2020 (AIC2020). The purpose of vehicle Re-ID is to retrieve the same vehicle appeared across multiple cameras, and it could make a great contribution to the Intelligent Traffic System(ITS) and smart city. Due to the vehicle's orientation, lighting and inter-class similarity, it is difficult to achieve robust and discriminative representation feature. For the vehicle Re-ID track in AIC2020, our method is to fuse features extracted from different networks in order to take advantages of these networks and achieve complementary features. For each single model, several methods such as multi-loss, filter grafting, semi-supervised are used to increase the representation ability as better as possible. Top performance in City-Scale Multi-Camera Vehicle Re-Identification demonstrated the advantage of our methods, and we got 5-th place in the vehicle Re-ID track of AIC2020. The codes are available at this https URL.

39.Understanding Dynamic Scenes using Graph Convolution Networks ⬇️

We present a novel Multi Relational Graph Convolutional Network (MRGCN) to model on-road vehicle behaviours from a sequence of temporally ordered frames as grabbed by a moving monocular camera. The input to MRGCN is a Multi Relational Graph (MRG) where the nodes of the graph represent the active and passive participants/agents in the scene while the bidrectional edges that connect every pair of nodes are encodings of the spatio-temporal relations. The bidirectional edges of the graph encode the temporal interactions between the agents that constitute the two nodes of the edge. The proposed method of obtaining his encoding is shown to be specifically suited for the problem at hand as it outperforms more complex end to end learning methods that do not use such intermediate representations of evolved spatio-temporal relations between agent pairs. We show significant performance gain in the form of behaviour classification accuracy on a variety of datasets from different parts of the globe over prior methods as well as show seamless transfer without any resort to fine-tuning across multiple datasets. Such behaviour prediction methods find immediate relevance in a variety of navigation tasks such as behaviour planning, state estimation as well as in applications relating to detection of traffic violations over videos.

40.Memory-Augmented Relation Network for Few-Shot Learning ⬇️

Metric-based few-shot learning methods concentrate on learning transferable feature embedding that generalizes well from seen categories to unseen categories under the supervision of limited number of labelled instances. However, most of them treat each individual instance in the working context separately without considering its relationships with the others. In this work, we investigate a new metric-learning method, Memory-Augmented Relation Network (MRN), to explicitly exploit these relationships. In particular, for an instance, we choose the samples that are visually similar from the working context, and perform weighted information propagation to attentively aggregate helpful information from the chosen ones to enhance its representation. In MRN, we also formulate the distance metric as a learnable relation module which learns to compare for similarity measurement, and augment the working context with memory slots, both contributing to its generality. We empirically demonstrate that MRN yields significant improvement over its ancestor and achieves competitive or even better performance when compared with other few-shot learning approaches on the two major benchmark datasets, i.e. miniImagenet and tieredImagenet.

41.High Resolution Face Age Editing ⬇️

Face age editing has become a crucial task in film post-production, and is also becoming popular for general purpose photography. Recently, adversarial training has produced some of the most visually impressive results for image manipulation, including the face aging/de-aging task. In spite of considerable progress, current methods often present visual artifacts and can only deal with low-resolution images. In order to achieve aging/de-aging with the high quality and robustness necessary for wider use, these problems need to be addressed. This is the goal of the present work. We present an encoder-decoder architecture for face age editing. The core idea of our network is to create both a latent space containing the face identity, and a feature modulation layer corresponding to the age of the individual. We then combine these two elements to produce an output image of the person with a desired target age. Our architecture is greatly simplified with respect to other approaches, and allows for continuous age editing on high resolution images in a single unified model.

42.Photo style transfer with consistency losses ⬇️

We address the problem of style transfer between two photos and propose a new way to preserve photorealism. Using the single pair of photos available as input, we train a pair of deep convolution networks (convnets), each of which transfers the style of one photo to the other. To enforce photorealism, we introduce a content preserving mechanism by combining a cycle-consistency loss with a self-consistency loss. Experimental results show that this method does not suffer from typical artifacts observed in methods working in the same settings. We then further analyze some properties of these trained convnets. First, we notice that they can be used to stylize other unseen images with same known style. Second, we show that retraining only a small subset of the network parameters can be sufficient to adapt these convnets to new styles.

43.A Weighted Difference of Anisotropic and Isotropic Total Variation for Relaxed Mumford-Shah Color and Multiphase Image Segmentation ⬇️

In a class of piecewise-constant image segmentation models, we incorporate a weighted difference of anisotropic and isotropic total variation (TV) to regularize the partition boundaries in an image. To deal with the weighted anisotropic-isotropic TV, we apply the difference-of-convex algorithm (DCA), where the subproblems can be minimized by the primal-dual hybrid gradient method (PDHG). As a result, we are able to design an alternating minimization algorithm to solve the proposed image segmentation models. The models and algorithms are further extended to segment color images and to perform multiphase segmentation. In the numerical experiments, we compare our proposed models with the Chan-Vese models that use either anisotropic or isotropic TV and the two-stage segmentation methods (denoising and then thresholding) on various images. The results demonstrate the effectiveness and robustness of incorporating weighted anisotropic-isotropic TV in image segmentation.

44.ICE-GAN: Identity-aware and Capsule-Enhanced GAN for Micro-Expression Recognition and Synthesis ⬇️

Micro-expressions can reflect peoples true feelings and motives, which attracts an increasing number of researchers into the studies of automatic facial micro-expression recognition (MER). The detection window of micro-expressions is too short in duration to be perceived by human eye, while their subtle face muscle movements also make MER a challenging task for pattern recognition. To this end, we propose a novel Identity-aware and Capsule-Enhanced Generative Adversarial Network (ICE-GAN), which is adversarially completed with the micro-expression synthesis (MES) task, where synthetic faces with controllable micro-expressions can be produced by the generator with distinguishable identity information to improve the MER performance. Meanwhile, the capsule-enhanced discriminator is optimized to simultaneously detect the authenticity and micro-expression class labels. Our ICE-GAN was evaluated on the 2nd Micro-Expression Grand Challenge (MEGC2019) and outperformed the winner by a significant margin (7%). To the best of our knowledge, we are the first work generating identity-preserving faces with different micro-expressions based on micro-expression datasets only.

45.Attentional Bottleneck: Towards an Interpretable Deep Driving Network ⬇️

Deep neural networks are a key component of behavior prediction and motion generation for self-driving cars. One of their main drawbacks is a lack of transparency: they should provide easy to interpret rationales for what triggers certain behaviors. We propose an architecture called Attentional Bottleneck with the goal of improving transparency. Our key idea is to combine visual attention, which identifies what aspects of the input the model is using, with an information bottleneck that enables the model to only use aspects of the input which are important. This not only provides sparse and interpretable attention maps (e.g. focusing only on specific vehicles in the scene), but it adds this transparency at no cost to model accuracy. In fact, we find slight improvements in accuracy when applying Attentional Bottleneck to the ChauffeurNet model, whereas we find that the accuracy deteriorates with a traditional visual attention model.

46.VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation ⬇️

Behavior prediction in dynamic, multi-agent systems is an important problem in the context of self-driving cars, due to the complex representations and interactions of road components, including moving agents (e.g. pedestrians and vehicles) and road context information (e.g. lanes, traffic lights). This paper introduces VectorNet, a hierarchical graph neural network that first exploits the spatial locality of individual road components represented by vectors and then models the high-order interactions among all components. In contrast to most recent approaches, which render trajectories of moving agents and road context information as bird-eye images and encode them with convolutional neural networks (ConvNets), our approach operates on a vector representation. By operating on the vectorized high definition (HD) maps and agent trajectories, we avoid lossy rendering and computationally intensive ConvNet encoding steps. To further boost VectorNet's capability in learning context features, we propose a novel auxiliary task to recover the randomly masked out map entities and agent trajectories based on their context. We evaluate VectorNet on our in-house behavior prediction benchmark and the recently released Argoverse forecasting dataset. Our method achieves on par or better performance than the competitive rendering approach on both benchmarks while saving over 70% of the model parameters with an order of magnitude reduction in FLOPs. It also outperforms the state of the art on the Argoverse dataset.

47.View Invariant Human Body Detection and Pose Estimation from Multiple Depth Sensors ⬇️

Point cloud based methods have produced promising results in areas such as 3D object detection in autonomous driving. However, most of the recent point cloud work focuses on single depth sensor data, whereas less work has been done on indoor monitoring applications, such as operation room monitoring in hospitals or indoor surveillance. In these scenarios multiple cameras are often used to tackle occlusion problems. We propose an end-to-end multi-person 3D pose estimation network, Point R-CNN, using multiple point cloud sources. We conduct extensive experiments to simulate challenging real world cases, such as individual camera failures, various target appearances, and complex cluttered scenes with the CMU panoptic dataset and the MVOR operation room dataset. Unlike most of the previous methods that attempt to use multiple sensor information by building complex fusion models, which often lead to poor generalization, we take advantage of the efficiency of concatenating point clouds to fuse the information at the input level. In the meantime, we show our end-to-end network greatly outperforms cascaded state-of-the-art models.

48.STINet: Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory Prediction ⬇️

Detecting pedestrians and predicting future trajectories for them are critical tasks for numerous applications, such as autonomous driving. Previous methods either treat the detection and prediction as separate tasks or simply add a trajectory regression head on top of a detector. In this work, we present a novel end-to-end two-stage network: Spatio-Temporal-Interactive Network (STINet). In addition to 3D geometry modeling of pedestrians, we model the temporal information for each of the pedestrians. To do so, our method predicts both current and past locations in the first stage, so that each pedestrian can be linked across frames and the comprehensive spatio-temporal information can be captured in the second stage. Also, we model the interaction among objects with an interaction graph, to gather the information among the neighboring objects. Comprehensive experiments on the Lyft Dataset and the recently released large-scale Waymo Open Dataset for both object detection and future trajectory prediction validate the effectiveness of the proposed method. For the Waymo Open Dataset, we achieve a bird-eyes-view (BEV) detection AP of 80.73 and trajectory prediction average displacement error (ADE) of 33.67cm for pedestrians, which establish the state-of-the-art for both tasks.

49.Fundus2Angio: A Novel Conditional GAN Architecture for Generating Fluorescein Angiography Images from Retinal Fundus Photography ⬇️

Carrying out clinical diagnosis of retinal vascular degeneration using Fluorescein Angiography (FA) is a time consuming process and can pose significant adverse effects on the patient. Angiography requires insertion of a dye that may cause severe adverse effects and can even be fatal. Currently, there are no non-invasive systems capable of generating Fluorescein Angiography images. However, retinal fundus photography is anon-invasive imaging technique that can be completed in a few seconds. In order to eliminate the need for FA, we propose a conditional generative adversarial network (GAN)to translate fundus images to FA images. The proposed GAN consists of a novel residual block capable of generating high quality FA images. These images are important tools in the differential diagnosis of retinal diseases without the need for invasive procedure with possible side effects. Our experiments show that the proposed architecture outperforms other state-of-the-art generative networks. Furthermore, our proposed model achieves better qualitative results indistinguishable from real angiograms.

50.iUNets: Fully invertible U-Nets with Learnable Up- and Downsampling ⬇️

U-Nets have been established as a standard neural network design architecture for image-to-image learning problems such as segmentation and inverse problems in imaging. For high-dimensional applications, as they for example appear in 3D medical imaging, U-Nets however have prohibitive memory requirements. Here, we present a new fully-invertible U-Net-based architecture called the \emph{iUNet}, which allows for the application of highly memory-efficient backpropagation procedures. For this, we introduce learnable and invertible up- and downsampling operations. An open source library in Pytorch for 1D, 2D and 3D data is made available.

51.Medical Image Segmentation Using a U-Net type of Architecture ⬇️

Deep convolutional neural networks have been proven to be very effective in image related analysis and tasks, such as image segmentation, image classification, image generation, etc. Recently many sophisticated CNN based architectures have been proposed for the purpose of image segmentation. Some of these newly designed networks are used for the specific purpose of medical image segmentation, models like V-Net, U-Net and their variants. It has been shown that U-Net produces very promising results in the domain of medical image segmentation.However, in this paper, we argue that the architecture of U-Net, when combined with a supervised training strategy at the bottleneck layer, can produce comparable results with the original U-Net architecture. More specifically, we introduce a fully supervised FC layers based pixel-wise loss at the bottleneck of the encoder branch of U-Net. The two layer based FC sub-net will train the bottleneck representation to contain more semantic information, which will be used by the decoder layers to predict the final segmentation map. The FC layer based sub-net is trained by employing the pixel-wise cross entropy loss, while the U-Net architectures trained by using L1 loss.

52.A Contrast-Adaptive Method for Simultaneous Whole-Brain and Lesion Segmentation in Multiple Sclerosis ⬇️

Here we present a method for the simultaneous segmentation of white matter lesions and normal-appearing neuroanatomical structures from multi-contrast brain MRI scans of multiple sclerosis patients. The method integrates a novel model for white matter lesions into a previously validated generative model for whole-brain segmentation. By using separate models for the shape of anatomical structures and their appearance in MRI, the algorithm can adapt to data acquired with different scanners and imaging protocols without retraining. We validate the method using three disparate datasets, showing state-of-the-art performance in white matter lesion segmentation while simultaneously segmenting dozens of other brain structures. We further demonstrate that the contrast-adaptive method can also be applied robustly to MRI scans of healthy controls, and replicate previously documented atrophy patterns in deep gray matter structures in MS. The algorithm is publicly available as part of the open-source neuroimaging package FreeSurfer.

53.A New Computer-Aided Diagnosis System with Modified Genetic Feature Selection for BI-RADS Classification of Breast Masses in Mammograms ⬇️

Mammography remains the most prevalent imaging tool for early breast cancer screening. The language used to describe abnormalities in mammographic reports is based on the breast Imaging Reporting and Data System (BI-RADS). Assigning a correct BI-RADS category to each examined mammogram is a strenuous and challenging task for even experts. This paper proposes a new and effective computer-aided diagnosis (CAD) system to classify mammographic masses into four assessment categories in BI-RADS. The mass regions are first enhanced by means of histogram equalization and then semiautomatically segmented based on the region growing technique. A total of 130 handcrafted BI-RADS features are then extrcated from the shape, margin, and density of each mass, together with the mass size and the patient's age, as mentioned in BI-RADS mammography. Then, a modified feature selection method based on the genetic algorithm (GA) is proposed to select the most clinically significant BI-RADS features. Finally, a back-propagation neural network (BPN) is employed for classification, and its accuracy is used as the fitness in GA. A set of 500 mammogram images from the digital database of screening mammography (DDSM) is used for evaluation. Our system achieves classification accuracy, positive predictive value, negative predictive value, and Matthews correlation coefficient of 84.5%, 84.4%, 94.8%, and 79.3%, respectively. To our best knowledge, this is the best current result for BI-RADS classification of breast masses in mammography, which makes the proposed system promising to support radiologists for deciding proper patient management based on the automatically assigned BI-RADS categories.

54.Autonomous Tissue Scanning under Free-Form Motion for Intraoperative Tissue Characterisation ⬇️

In Minimally Invasive Surgery (MIS), tissue scanning with imaging probes is required for subsurface visualisation to characterise the state of the tissue. However, scanning of large tissue surfaces in the presence of deformation is a challenging task for the surgeon. Recently, robot-assisted local tissue scanning has been investigated for motion stabilisation of imaging probes to facilitate the capturing of good quality images and reduce the surgeon's cognitive load. Nonetheless, these approaches require the tissue surface to be static or deform with periodic motion. To eliminate these assumptions, we propose a visual servoing framework for autonomous tissue scanning, able to deal with free-form tissue deformation. The 3D structure of the surgical scene is recovered and a feature-based method is proposed to estimate the motion of the tissue in real-time. A desired scanning trajectory is manually defined on a reference frame and continuously updated using projective geometry to follow the tissue motion and control the movement of the robotic arm. The advantage of the proposed method is that it does not require the learning of the tissue motion prior to scanning and can deal with free-form deformation. We deployed this framework on the da Vinci surgical robot using the da Vinci Research Kit (dVRK) for Ultrasound tissue scanning. Since the framework does not rely on information from the Ultrasound data, it can be easily extended to other probe-based imaging modalities.

55.Deep Reinforcement Learning for Organ Localization in CT ⬇️

Robust localization of organs in computed tomography scans is a constant pre-processing requirement for organ-specific image retrieval, radiotherapy planning, and interventional image analysis. In contrast to current solutions based on exhaustive search or region proposals, which require large amounts of annotated data, we propose a deep reinforcement learning approach for organ localization in CT. In this work, an artificial agent is actively self-taught to localize organs in CT by learning from its asserts and mistakes. Within the context of reinforcement learning, we propose a novel set of actions tailored for organ localization in CT. Our method can use as a plug-and-play module for localizing any organ of interest. We evaluate the proposed solution on the public VISCERAL dataset containing CT scans with varying fields of view and multiple organs. We achieved an overall intersection over union of 0.63, an absolute median wall distance of 2.25 mm, and a median distance between centroids of 3.65 mm.

56.Learning to hash with semantic similarity metrics and empirical KL divergence ⬇️

Learning to hash is an efficient paradigm for exact and approximate nearest neighbor search from massive databases. Binary hash codes are typically extracted from an image by rounding output features from a CNN, which is trained on a supervised binary similar/ dissimilar task. Drawbacks of this approach are: (i) resulting codes do not necessarily capture semantic similarity of the input data (ii) rounding results in information loss, manifesting as decreased retrieval performance and (iii) Using only class-wise similarity as a target can lead to trivial solutions, simply encoding classifier outputs rather than learning more intricate relations, which is not detected by most performance metrics. We overcome (i) via a novel loss function encouraging the relative hash code distances of learned features to match those derived from their targets. We address (ii) via a differentiable estimate of the KL divergence between network outputs and a binary target distribution, resulting in minimal information loss when the features are rounded to binary. Finally, we resolve (iii) by focusing on a hierarchical precision metric. Efficiency of the methods is demonstrated with semantic image retrieval on the CIFAR-100, ImageNet and Conceptual Captions datasets, using similarities inferred from the WordNet label hierarchy or sentence embeddings.

57.Gleason Score Prediction using Deep Learning in Tissue Microarray Image ⬇️

Prostate cancer (PCa) is one of the most common cancers in men around the world. The most accurate method to evaluate lesion levels of PCa is microscopic inspection of stained biopsy tissue and estimate the Gleason score of tissue microarray (TMA) image by expert pathologists. However, it is time-consuming for pathologists to identify the cellular and glandular patterns for Gleason grading in large TMA images. We used Gleason2019 Challenge dataset to build a convolutional neural network (CNN) model to segment TMA images to regions of different Gleason grades and predict the Gleason score according to the grading segmentation. We used a pre-trained model of prostate segmentation to increase the accuracy of the Gleason grade segmentation. The model achieved a mean Dice of 75.6% on the test cohort and ranked 4th in the Gleason2019 Challenge with a score of 0.778 combined of Cohen's kappa and the f1-score.

58.The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes ⬇️

This work proposes a new challenge set for multimodal classification, focusing on detecting hate speech in multimodal memes. It is constructed such that unimodal models struggle and only multimodal models can succeed: difficult examples ("benign confounders") are added to the dataset to make it hard to rely on unimodal signals. The task requires subtle reasoning, yet is straightforward to evaluate as a binary classification problem. We provide baseline performance numbers for unimodal models, as well as for multimodal models with various degrees of sophistication. We find that state-of-the-art methods perform poorly compared to humans (64.73% vs. 84.7% accuracy), illustrating the difficulty of the task and highlighting the challenge that this important problem poses to the community.

59.Hierarchical Regression Network for Spectral Reconstruction from RGB Images ⬇️

Capturing visual image with a hyperspectral camera has been successfully applied to many areas due to its narrow-band imaging technology. Hyperspectral reconstruction from RGB images denotes a reverse process of hyperspectral imaging by discovering an inverse response function. Current works mainly map RGB images directly to corresponding spectrum but do not consider context information explicitly. Moreover, the use of encoder-decoder pair in current algorithms leads to loss of information. To address these problems, we propose a 4-level Hierarchical Regression Network (HRNet) with PixelShuffle layer as inter-level interaction. Furthermore, we adopt a residual dense block to remove artifacts of real world RGB images and a residual global block to build attention mechanism for enlarging perceptive field. We evaluate proposed HRNet with other architectures and techniques by participating in NTIRE 2020 Challenge on Spectral Reconstruction from RGB Images. The HRNet is the winning method of track 2 - real world images and ranks 3rd on track 1 - clean images. Please visit the project web page this https URL to try our codes and pre-trained models.

60.Segmentation of Macular Edema Datasets with Small Residual 3D U-Net Architectures ⬇️

This paper investigates the application of deep convolutional neural networks with prohibitively small datasets to the problem of macular edema segmentation. In particular, we investigate several different heavily regularized architectures. We find that, contrary to popular belief, neural architectures within this application setting are able to achieve close to human-level performance on unseen test images without requiring large numbers of training examples. Annotating these 3D datasets is difficult, with multiple criteria required. It takes an experienced clinician two days to annotate a single 3D image, whereas our trained model achieves similar performance in less than a second. We found that an approach which uses targeted dataset augmentation, alongside architectural simplification with an emphasis on residual design, has acceptable generalization performance - despite relying on fewer than 15 training examples.

61.Non-Autoregressive Image Captioning with Counterfactuals-Critical Multi-Agent Learning ⬇️

Most image captioning models are autoregressive, i.e. they generate each word by conditioning on previously generated words, which leads to heavy latency during inference. Recently, non-autoregressive decoding has been proposed in machine translation to speed up the inference time by generating all words in parallel. Typically, these models use the word-level cross-entropy loss to optimize each word independently. However, such a learning process fails to consider the sentence-level consistency, thus resulting in inferior generation quality of these non-autoregressive models. In this paper, we propose a Non-Autoregressive Image Captioning (NAIC) model with a novel training paradigm: Counterfactuals-critical Multi-Agent Learning (CMAL). CMAL formulates NAIC as a multi-agent reinforcement learning system where positions in the target sequence are viewed as agents that learn to cooperatively maximize a sentence-level reward. Besides, we propose to utilize massive unlabeled images to boost captioning performance. Extensive experiments on MSCOCO image captioning benchmark show that our NAIC model achieves a performance comparable to state-of-the-art autoregressive models, while brings 13.9x decoding speedup.

62.Learning Context-Based Non-local Entropy Modeling for Image Compression ⬇️

The entropy of the codes usually serves as the rate loss in the recent learned lossy image compression methods. Precise estimation of the probabilistic distribution of the codes plays a vital role in the performance. However, existing deep learning based entropy modeling methods generally assume the latent codes are statistically independent or depend on some side information or local context, which fails to take the global similarity within the context into account and thus hinder the accurate entropy estimation. To address this issue, we propose a non-local operation for context modeling by employing the global similarity within the context. Specifically, we first introduce the proxy similarity functions and spatial masks to handle the missing reference problem in context modeling. Then, we combine the local and the global context via a non-local attention block and employ it in masked convolutional networks for entropy modeling. The entropy model is further adopted as the rate loss in a joint rate-distortion optimization to guide the training of the analysis transform and the synthesis transform network in transforming coding framework. Considering that the width of the transforms is essential in training low distortion models, we finally produce a U-Net block in the transforms to increase the width with manageable memory consumption and time complexity. Experiments on Kodak and Tecnick datasets demonstrate the superiority of the proposed context-based non-local attention block in entropy modeling and the U-Net block in low distortion compression against the existing image compression standards and recent deep image compression models.

63.BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps ⬇️

Learning to follow instructions is of fundamental importance to autonomous agents for vision-and-language navigation (VLN). In this paper, we study how an agent can navigate long paths when learning from a corpus that consists of shorter ones. We show that existing state-of-the-art agents do not generalize well. To this end, we propose BabyWalk, a new VLN agent that is learned to navigate by decomposing long instructions into shorter ones (BabySteps) and completing them sequentially. A special design memory buffer is used by the agent to turn its past experiences into contexts for future steps. The learning process is composed of two phases. In the first phase, the agent uses imitation learning from demonstration to accomplish BabySteps. In the second phase, the agent uses curriculum-based reinforcement learning to maximize rewards on navigation tasks with increasingly longer instructions. We create two new benchmark datasets (of long navigation tasks) and use them in conjunction with existing ones to examine BabyWalk's generalization ability. Empirical results show that BabyWalk achieves state-of-the-art results on several metrics, in particular, is able to follow long instructions better. The codes and the datasets are released on our project page this https URL.

64.Duality in Persistent Homology of Images ⬇️

We derive the relationship between the persistent homology barcodes of two dual filtered CW complexes. Applied to greyscale digital images, we obtain an algorithm to convert barcodes between the two different (dual) topological models of pixel connectivity.

65.A Hybrid Swarm and Gravitation based feature selection algorithm for Handwritten Indic Script Classification problem ⬇️

In any multi-script environment, handwritten script classification is of paramount importance before the document images are fed to their respective Optical Character Recognition (OCR) engines. Over the years, this complex pattern classification problem has been solved by researchers proposing various feature vectors mostly having large dimension, thereby increasing the computation complexity of the whole classification model. Feature Selection (FS) can serve as an intermediate step to reduce the size of the feature vectors by restricting them only to the essential and relevant features. In our paper, we have addressed this issue by introducing a new FS algorithm, called Hybrid Swarm and Gravitation based FS (HSGFS). This algorithm is made to run on 3 feature vectors introduced in the literature recently - Distance-Hough Transform (DHT), Histogram of Oriented Gradients (HOG) and Modified log-Gabor (MLG) filter Transform. Three state-of-the-art classifiers namely, Multi-Layer Perceptron (MLP), K-Nearest Neighbour (KNN) and Support Vector Machine (SVM) are used for the handwritten script classification. Handwritten datasets, prepared at block, text-line and word level, consisting of officially recognized 12 Indic scripts are used for the evaluation of our method. An average improvement in the range of 2-5 % is achieved in the classification accuracies by utilizing only about 75-80 % of the original feature vectors on all three datasets. The proposed methodology also shows better performance when compared to some popularly used FS models.

66.An Integrated Enhancement Solution for 24-hour Colorful Imaging ⬇️

The current industry practice for 24-hour outdoor imaging is to use a silicon camera supplemented with near-infrared (NIR) illumination. This will result in color images with poor contrast at daytime and absence of chrominance at nighttime. For this dilemma, all existing solutions try to capture RGB and NIR images separately. However, they need additional hardware support and suffer from various drawbacks, including short service life, high price, specific usage scenario, etc. In this paper, we propose a novel and integrated enhancement solution that produces clear color images, whether at abundant sunlight daytime or extremely low-light nighttime. Our key idea is to separate the VIS and NIR information from mixed signals, and enhance the VIS signal adaptively with the NIR signal as assistance. To this end, we build an optical system to collect a new VIS-NIR-MIX dataset and present a physically meaningful image processing algorithm based on CNN. Extensive experiments show outstanding results, which demonstrate the effectiveness of our solution.

67.A Survey on Deep Learning for Neuroimaging-based Brain Disorder Analysis ⬇️

Deep learning has been recently used for the analysis of neuroimages, such as structural magnetic resonance imaging (MRI), functional MRI, and positron emission tomography (PET), and has achieved significant performance improvements over traditional machine learning in computer-aided diagnosis of brain disorders. This paper reviews the applications of deep learning methods for neuroimaging-based brain disorder analysis. We first provide a comprehensive overview of deep learning techniques and popular network architectures, by introducing various types of deep neural networks and recent developments. We then review deep learning methods for computer-aided analysis of four typical brain disorders, including Alzheimer's disease, Parkinson's disease, Autism spectrum disorder, and Schizophrenia, where the first two diseases are neurodegenerative disorders and the last two are neurodevelopmental and psychiatric disorders, respectively. More importantly, we discuss the limitations of existing studies and present possible future directions.

68.Non-recurrent Traffic Congestion Detection with a Coupled Scalable Bayesian Robust Tensor Factorization Model ⬇️

Non-recurrent traffic congestion (NRTC) usually brings unexpected delays to commuters. Hence, it is critical to accurately detect and recognize the NRTC in a real-time manner. The advancement of road traffic detectors and loop detectors provides researchers with a large-scale multivariable temporal-spatial traffic data, which allows the deep research on NRTC to be conducted. However, it remains a challenging task to construct an analytical framework through which the natural spatial-temporal structural properties of multivariable traffic information can be effectively represented and exploited to better understand and detect NRTC. In this paper, we present a novel analytical training-free framework based on coupled scalable Bayesian robust tensor factorization (Coupled SBRTF). The framework can couple multivariable traffic data including traffic flow, road speed, and occupancy through sharing a similar or the same sparse structure. And, it naturally captures the high-dimensional spatial-temporal structural properties of traffic data by tensor factorization. With its entries revealing the distribution and magnitude of NRTC, the shared sparse structure of the framework compasses sufficiently abundant information about NRTC. While the low-rank part of the framework, expresses the distribution of general expected traffic condition as an auxiliary product. Experimental results on real-world traffic data show that the proposed method outperforms coupled Bayesian robust principal component analysis (coupled BRPCA), the rank sparsity tensor decomposition (RSTD), and standard normal deviates (SND) in detecting NRTC. The proposed method performs even better when only traffic data in weekdays are utilized, and hence can provide more precise estimation of NRTC for daily commuters.

69.Efficient Privacy Preserving Edge Computing Framework for Image Classification ⬇️

In order to extract knowledge from the large data collected by edge devices, traditional cloud based approach that requires data upload may not be feasible due to communication bandwidth limitation as well as privacy and security concerns of end users. To address these challenges, a novel privacy preserving edge computing framework is proposed in this paper for image classification. Specifically, autoencoder will be trained unsupervised at each edge device individually, then the obtained latent vectors will be transmitted to the edge server for the training of a classifier. This framework would reduce the communications overhead and protect the data of the end users. Comparing to federated learning, the training of the classifier in the proposed framework does not subject to the constraints of the edge devices, and the autoencoder can be trained independently at each edge device without any server involvement. Furthermore, the privacy of the end users' data is protected by transmitting latent vectors without additional cost of encryption. Experimental results provide insights on the image classification performance vs. various design parameters such as the data compression ratio of the autoencoder and the model complexity.

70.Building a Manga Dataset "Manga109" with Annotations for Multimedia Applications ⬇️

Manga, or comics, which are a type of multimodal artwork, have been left behind in the recent trend of deep learning applications because of the lack of a proper dataset. Hence, we built Manga109, a dataset consisting of a variety of 109 Japanese comic books (94 authors and 21,142 pages) and made it publicly available by obtaining author permissions for academic use. We carefully annotated the frames, speech texts, character faces, and character bodies; the total number of annotations exceeds 500k. This dataset provides numerous manga images and annotations, which will be beneficial for use in machine learning algorithms and their evaluation. In addition to academic use, we obtained further permission for a subset of the dataset for industrial use. In this article, we describe the details of the dataset and present a few examples of multimedia processing applications (detection, retrieval, and generation) that apply existing deep learning methods and are made possible by the dataset.

71.Comment on "No-Reference Video Quality Assessment Based on the Temporal Pooling of Deep Features" ⬇️

In Neural Processing Letters 50,3 (2019) a machine learning approach to blind video quality assessment was proposed. It is based on temporal pooling of features of video frames, taken from the last pooling layer of deep convolutional neural networks. The method was validated on two established benchmark datasets and gave results far better than the previous state-of-the-art. In this letter we report the results from our careful reimplementations. The performance results, claimed in the paper, cannot be reached, and are even below the state-of-the-art by a large margin. We show that the originally reported wrong performance results are a consequence of two cases of data leakage. Information from outside the training dataset was used in the fine-tuning stage and in the model evaluation.

72.Enhancing LGMD's Looming Selectivity for UAVs with Spatial-temporal Distributed Presynaptic Connection ⬇️

Collision detection is one of the most challenging tasks for Unmanned Aerial Vehicles (UAVs), especially for small or micro UAVs with limited computational power. In nature, fly insects with compact and simple visual systems demonstrate the amazing ability to navigating and avoid collision in a complex environment. A good example of this is locusts. Locusts avoid collision in a dense swarm relying on an identified vision neuron called Lobula Giant Movement Detector (LGMD) which has been modelled and applied on ground robots and vehicles. LGMD as a fly insect's visual neuron, is an ideal model for UAV collision detection. However, the existing models are inadequate in coping with complex visual challenges unique for UAVs. In this paper, we proposed a new LGMD model for flying robots considering distributed spatial-temporal computing for both excitation and inhibition to enhance the looming selectivity in flying scenes. The proposed model integrated recent discovered presynaptic connection types in biological LGMD neuron into a spatial-temporal filter with linear distributed interconnection. Systematic experiments containing quadcopter's first person view (FPV) flight videos demonstrated that the proposed distributed presynaptic structure can dramatically enhance LGMD's looming selectivity especially in complex flying UAV applications.

73.AutoCLINT: The Winning Method in AutoCV Challenge 2019 ⬇️

NeurIPS 2019 AutoDL challenge is a series of six automated machine learning competitions. Particularly, AutoCV challenges mainly focused on classification tasks on visual domain. In this paper, we introduce the winning method in the competition, AutoCLINT. The proposed method implements an autonomous training strategy, including efficient code optimization, and applies an automated data augmentation to achieve the fast adaptation of pretrained networks. We implement a light version of Fast AutoAugment to search for data augmentation policies efficiently for the arbitrarily given image domains. We also empirically analyze the components of the proposed method and provide ablation studies focusing on AutoCV datasets.

74.An Investigation of Why Overparameterization Exacerbates Spurious Correlations ⬇️

We study why overparameterization -- increasing model size well beyond the point of zero training error -- can hurt test error on minority groups despite improving average test error when there are spurious correlations in the data. Through simulations and experiments on two image datasets, we identify two key properties of the training data that drive this behavior: the proportions of majority versus minority groups, and the signal-to-noise ratio of the spurious correlations. We then analyze a linear setting and show theoretically how the inductive bias of models towards "memorizing" fewer examples can cause overparameterization to hurt. Our analysis leads to a counterintuitive approach of subsampling the majority group, which empirically achieves low minority error in the overparameterized regime, even though the standard approach of upweighting the minority fails. Overall, our results suggest a tension between using overparameterized models versus using all the training data for achieving low worst-group error.

75.ST-MNIST -- The Spiking Tactile MNIST Neuromorphic Dataset ⬇️

Tactile sensing is an essential modality for smart robots as it enables them to interact flexibly with physical objects in their environment. Recent advancements in electronic skins have led to the development of data-driven machine learning methods that exploit this important sensory modality. However, current datasets used to train such algorithms are limited to standard synchronous tactile sensors. There is a dearth of neuromorphic event-based tactile datasets, principally due to the scarcity of large-scale event-based tactile sensors. Having such datasets is crucial for the development and evaluation of new algorithms that process spatio-temporal event-based data. For example, evaluating spiking neural networks on conventional frame-based datasets is considered sub-optimal. Here, we debut a novel neuromorphic Spiking Tactile MNIST (ST-MNIST) dataset, which comprises handwritten digits obtained by human participants writing on a neuromorphic tactile sensor array. We also describe an initial effort to evaluate our ST-MNIST dataset using existing artificial and spiking neural network models. The classification accuracies provided herein can serve as performance benchmarks for future work. We anticipate that our ST-MNIST dataset will be of interest and useful to the neuromorphic and robotics research communities.

76.Progressive Adversarial Semantic Segmentation ⬇️

Medical image computing has advanced rapidly with the advent of deep learning techniques such as convolutional neural networks. Deep convolutional neural networks can perform exceedingly well given full supervision. However, the success of such fully-supervised models for various image analysis tasks (e.g., anatomy or lesion segmentation from medical images) is limited to the availability of massive amounts of labeled data. Given small sample sizes, such models are prohibitively data biased with large domain shift. To tackle this problem, we propose a novel end-to-end medical image segmentation model, namely Progressive Adversarial Semantic Segmentation (PASS), which can make improved segmentation predictions without requiring any domain-specific data during training time. Our extensive experimentation with 8 public diabetic retinopathy and chest X-ray datasets, confirms the effectiveness of PASS for accurate vascular and pulmonary segmentation, both for in-domain and cross-domain evaluations.

77.Measuring the Algorithmic Efficiency of Neural Networks ⬇️

Three factors drive the advance of AI: algorithmic innovation, data, and the amount of compute available for training. Algorithmic progress has traditionally been more difficult to quantify than compute and data. In this work, we argue that algorithmic progress has an aspect that is both straightforward to measure and interesting: reductions over time in the compute needed to reach past capabilities. We show that the number of floating-point operations required to train a classifier to AlexNet-level performance on ImageNet has decreased by a factor of 44x between 2012 and 2019. This corresponds to algorithmic efficiency doubling every 16 months over a period of 7 years. By contrast, Moore's Law would only have yielded an 11x cost improvement. We observe that hardware and algorithmic efficiency gains multiply and can be on a similar scale over meaningful horizons, which suggests that a good model of AI progress should integrate measures from both.

78.Deep Residual Network based food recognition for enhanced Augmented Reality application ⬇️

Deep neural network based learning approaches is widely utilized for image classification or object detection based problems with remarkable outcomes. Realtime Object state estimation of objects can be used to track and estimate the features that the object of the current frame possesses without causing any significant delay and misclassification. A system that can detect the features of such objects in the present state from camera images can be used to enhance the application of Augmented Reality for improving user experience and delivering information in a much perceptual way. The focus behind this paper is to determine the most suitable model to create a low-latency assistance AR to aid users by providing them nutritional information about the food that they consume in order to promote healthier life choices. Hence the dataset has been collected and acquired in such a manner, and we conduct various tests in order to identify the most suitable DNN in terms of performance and complexity and establish a system that renders such information realtime to the user.