Search

This paper presents a novel framework to recover detailed avatar from a single image. It is a challenging task due to factors such as variations in human shapes, body poses, texture, and viewpoints. Prior methods typically attempt to recover the human body shape using a parametric-based template that lacks the surface details. As such resulting body shape appears to be without clothing. In this paper, we propose a novel learning-based framework that combines the robustness of the parametric model with the flexibility of free-form 3D deformation. We use the deep neural networks to refine the 3D shape in a Hierarchical Mesh Deformation (HMD) framework, utilizing the constraints from body joints, silhouettes, and per-pixel shading information. Our method can restore detailed human body shapes with complete textures beyond skinned models. Experiments demonstrate that our method has outperformed previous state-of-the-art approaches, achieving better accuracy in terms of both 2D IoU number and 3D metric distance. [ABSTRACT FROM AUTHOR]

This paper serves as a survey of recent advances in large margin training and its theoretical foundations, mostly for (nonlinear) deep neural networks (DNNs) that are probably the most prominent machine learning models for large-scale data in the community over the past decade. We generalize the formulation of classification margins from classical research to latest DNNs, summarize theoretical connections between the margin, network generalization, and robustness, and introduce recent efforts in enlarging the margins for DNNs comprehensively. Since the viewpoint of different methods is discrepant, we categorize them into groups for ease of comparison and discussion in the paper. Hopefully, our discussions and overview inspire new research work in the community that aim to improve the performance of DNNs, and we also point to directions where the large margin principle can be verified to provide theoretical evidence why certain regularizations for DNNs function well in practice. We managed to shorten the paper such that the crucial spirit of large margin learning and related methods are better emphasized. [ABSTRACT FROM AUTHOR]

Correspondence analysis (CA) is a multivariate statistical tool used to visualize and interpret data dependencies by finding maximally correlated embeddings of pairs of random variables. CA has found applications in fields ranging from epidemiology to social sciences. However, current methods for CA do not scale to large, high-dimensional datasets. In this paper, we provide a novel interpretation of CA in terms of an information-theoretic quantity called the principal inertia components. We show that estimating the principal inertia components, which consists in solving a functional optimization problem over the space of finite variance functions of two random variable, is equivalent to performing CA. We then leverage this insight to design algorithms to perform CA at scale. Specifically, we demonstrate how the principal inertia components can be reliably approximated from data using deep neural networks. Finally, we show how the maximally correlated embeddings of pairs of random variables in CA further play a central role in several learning problems including multi-view and multi-modal learning methods and visualization of classification boundaries. [ABSTRACT FROM AUTHOR]

Deep neural networks have been tremendously successful at segmenting objects in images. However, it has been shown they still have limitations on challenging problems such as the segmentation of medical images. The main reason behind this lower success resides in the reduced size of the object in the image. In this paper we overcome this limitation through a cyclic collaborative framework, CyCoSeg. The proposed framework is based on a deep active shape model (D-ASM), which provides prior information about the shape of the object, and a semantic segmentation network (SSN). These two models collaborate to reach the desired segmentation by influencing each other: SSN helps D-ASM identify relevant keypoints in the image through an Expectation Maximization formulation, while D-ASM provides a segmentation proposal that guides the SSN. This cycle is repeated until both models converge. Extensive experimental evaluation shows CyCoSeg boosts the performance of the baseline models, including several popular SSNs, while avoiding major architectural modifications. The effectiveness of our method is demonstrated on the left ventricle segmentation on two benchmark datasets, where our approach achieves one of the most competitive results in segmentation accuracy. Furthermore, its generalization is demonstrated for lungs and kidneys segmentation in CT scans. [ABSTRACT FROM AUTHOR]

In this paper, we consider how to incorporate psychophysical measurements of human visual perception into the loss function of a deep neural network being trained for a recognition task, under the assumption that such information can reduce errors. As a case study to assess the viability of this approach, we look at the problem of handwritten document transcription. While good progress has been made towards automatically transcribing modern handwriting, significant challenges remain in transcribing historical documents. Here we describe a general enhancement strategy, underpinned by the new loss formulation, which can be applied to the training regime of any deep learning-based document transcription system. Through experimentation, reliable performance improvement is demonstrated for the standard IAM and RIMES datasets for three different network architectures. Further, we go on to show feasibility for our approach on a new dataset of digitized Latin manuscripts, originally produced by scribes in the Cloister of St. Gall in the the 9th century. [ABSTRACT FROM AUTHOR]

Object attention maps generated by image classifiers are usually used as priors for weakly supervised semantic segmentation. However, attention maps usually locate the most discriminative object parts. The lack of integral object localization maps heavily limits the performance of weakly supervised segmentation approaches. This paper attempts to investigate a novel way to identify entire object regions in a weakly supervised manner. We observe that image classifiers’ attention maps at different training phases may focus on different parts of the target objects. Based on this observation, we propose an online attention accumulation (OAA) strategy that utilizes the attention maps at different training phases to obtain more integral object regions. Specifically, we maintain a cumulative attention map for each target category in each training image and utilize it to record the discovered object regions at different training phases. Albeit OAA can effectively mine more object regions for most images, for some training images, the range of the attention movement is not large, limiting the generation of integral object attention regions. To overcome this problem, we propose incorporating an attention drop layer into the online attention accumulation process to enlarge the range of attention movement during training explicitly. Our method (OAA) can be plugged into any classification network and progressively accumulate the discriminative regions into cumulative attention maps as the training process goes. Additionally, we also explore utilizing the final cumulative attention maps to serve as the pixel-level supervision, which can further assist the network in discovering more integral object regions. When applying the resulting attention maps to the weakly supervised semantic segmentation task, our approach improves the existing state-of-the-art methods on the PASCAL VOC 2012 segmentation benchmark, achieving a mIoU score of 67.2 percent on the test set. [ABSTRACT FROM AUTHOR]

This paper tackles the problem of training a deep convolutional neural network of both low-bitwidth weights and activations. Optimizing a low-precision network is very challenging due to the non-differentiability of the quantizer, which may result in substantial accuracy loss. To address this, we propose three practical approaches, including (i) progressive quantization; (ii) stochastic precision; and (iii) joint knowledge distillation to improve the network training. First, for progressive quantization, we propose two schemes to progressively find good local minima. Specifically, we propose to first optimize a network with quantized weights and subsequently quantize activations. This is in contrast to the traditional methods which optimize them simultaneously. Furthermore, we propose a second progressive quantization scheme which gradually decreases the bitwidth from high-precision to low-precision during training. Second, to alleviate the excessive training burden due to the multi-round training stages, we further propose a one-stage stochastic precision strategy to randomly sample and quantize sub-networks while keeping other parts in full-precision. Finally, we adopt a novel learning scheme to jointly train a full-precision model alongside the low-precision one. By doing so, the full-precision model provides hints to guide the low-precision model training and significantly improves the performance of the low-precision network. Extensive experiments on various datasets (e.g., CIFAR-100, ImageNet) show the effectiveness of the proposed methods. [ABSTRACT FROM AUTHOR]

In this paper, we propose a pose grammar to tackle the problem of 3D human pose estimation from a monocular RGB image. Our model takes estimated 2D pose as the input and learns a generalized 2D-3D mapping function to leverage into 3D pose. The proposed model consists of a base network which efficiently captures pose-aligned features and a hierarchy of Bi-directional RNNs (BRNNs) on the top to explicitly incorporate a set of knowledge regarding human body configuration (i.e., kinematics, symmetry, motor coordination). The proposed model thus enforces high-level constraints over human poses. In learning, we develop a data augmentation algorithm to further improve model robustness against appearance variations and cross-view generalization ability. We validate our method on public 3D human pose benchmarks and propose a new evaluation protocol working on cross-view setting to verify the generalization capability of different methods. We empirically observe that most state-of-the-art methods encounter difficulty under such setting while our method can well handle such challenges. [ABSTRACT FROM AUTHOR]

A lot of work has been done towards reconstructing the 3D facial structure from single images by capitalizing on the power of deep convolutional neural networks (DCNNs). In the recent works, the texture features either correspond to components of a linear texture space or are learned by auto-encoders directly from in-the-wild images. In all cases, the quality of the facial texture reconstruction is still not capable of modeling facial texture with high-frequency details. In this paper, we take a radically different approach and harness the power of generative adversarial networks (GANs) and DCNNs in order to reconstruct the facial texture and shape from single images. That is, we utilize GANs to train a very powerful facial texture prior from a large-scale 3D texture dataset. Then, we revisit the original 3D Morphable Models (3DMMs) fitting making use of non-linear optimization to find the optimal latent parameters that best reconstruct the test image but under a new perspective. In order to be robust towards initialisation and expedite the fitting process, we propose a novel self-supervised regression based approach. We demonstrate excellent results in photorealistic and identity preserving 3D face reconstructions and achieve for the first time, to the best of our knowledge, facial texture reconstruction with high-frequency details. [ABSTRACT FROM AUTHOR]

Contextual information plays an important role in solving various image and scene understanding tasks. Prior works have focused on the extraction of contextual information from an image and use it to infer the properties of some object(s) in the image or understand the scene behind the image, e.g., context-based object detection, recognition and semantic segmentation. In this paper, we consider an inverse problem, i.e., how to hallucinate the missing contextual information from the properties of standalone objects. We refer to it as object-level scene context prediction. This problem is difficult, as it requires extensive knowledge of the complex and diverse relationships among objects in the scene. We propose a deep neural network, which takes as input the properties (i.e., category, shape, and position) of a few standalone objects to predict an object-level scene layout that compactly encodes the semantics and structure of the scene context where the given objects are. Quantitative experiments and user studies demonstrate that our model can generate more plausible scene contexts than the baselines. Our model also enables the synthesis of realistic scene images from partial scene layouts. Finally, we validate that our model internally learns useful features for scene recognition and fake scene detection. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (DCNNs) are currently the method of choice both for generative, as well as for discriminative learning in computer vision and machine learning. The success of DCNNs can be attributed to the careful selection of their building blocks (e.g., residual blocks, rectifiers, sophisticated normalization schemes, to mention but a few). In this paper, we propose $\Pi$ Π -Nets, a new class of function approximators based on polynomial expansions. $\Pi$ Π -Nets are polynomial neural networks, i.e., the output is a high-order polynomial of the input. The unknown parameters, which are naturally represented by high-order tensors, are estimated through a collective tensor factorization with factors sharing. We introduce three tensor decompositions that significantly reduce the number of parameters and show how they can be efficiently implemented by hierarchical neural networks. We empirically demonstrate that $\Pi$ Π -Nets are very expressive and they even produce good results without the use of non-linear activation functions in a large battery of tasks and signals, i.e., images, graphs, and audio. When used in conjunction with activation functions, $\Pi$ Π -Nets produce state-of-the-art results in three challenging tasks, i.e., image generation, face verification and 3D mesh representation learning. The source code is available at https://github.com/grigorisg9gr/polynomial_nets. [ABSTRACT FROM AUTHOR]

A sum-product network (SPN) is a probabilistic model, based on a rooted acyclic directed graph, in which terminal nodes represent probability distributions and non-terminal nodes represent convex sums (weighted averages) and products of probability distributions. They are closely related to probabilistic graphical models, in particular to Bayesian networks with multiple context-specific independencies. Their main advantage is the possibility of building tractable models from data, i.e., models that can perform several inference tasks in time proportional to the number of edges in the graph. They are somewhat similar to neural networks and can address the same kinds of problems, such as image processing and natural language understanding. This paper offers a survey of SPNs, including their definition, the main algorithms for inference and learning from data, several applications, a brief review of software libraries, and a comparison with related models. [ABSTRACT FROM AUTHOR]

In this paper, we propose a binarized neural network learning method (BiDet) for efficient object detection. Conventional network binarization methods directly quantize the weights and activations in one-stage or two-stage detectors with constrained representational capacity, so that the information redundancy in the networks causes numerous false positives and degrades the performance significantly. On the contrary, our BiDet fully utilizes the representational capacity of the binary neural networks by redundancy removal, through which the detection precision is enhanced with alleviated false positives. Specifically, we generalize the information bottleneck (IB) principle to object detection, where the amount of information in the high-level feature maps is constrained and the mutual information between the feature maps and object detection is maximized. Meanwhile, we learn sparse object priors so that the posteriors are concentrated on informative detection prediction with false positive elimination. Since BiDet employs a fixed IB trade-off to balance the total and relative information contained in the high-level feature maps, the information compression leads to ineffective utilization of the network capacity or insufficient redundancy removal for input in different complexity. To address this, we further present binary neural networks with automatic information compression (AutoBiDet) to automatically adjust the IB trade-off for each input according to the complexity. Moreover, we further propose the class-aware sparse object priors by assigning different sparsity to objects in various classes, so that the false positives are alleviated more effectively without recall decrease. Extensive experiments on the PASCAL VOC and COCO datasets show that our BiDet and AutoBiDet outperform the state-of-the-art binarized object detectors by a sizable margin. [ABSTRACT FROM AUTHOR]

There has been a resurgence of research in the design of deep architecture models and learning algorithms, i.e., methods that rely on the extraction of a multilayer representation of the data. Often referred to as deep learning, this topic of research has been building on and contributing to many different research topics, such as neural networks, graphical models, feature learning, unsupervised learning, optimization, pattern recognition, and signal processing. Deep learning is also motivated and inspired by neuroscience and has had a tremendous impact on various applications such as computer vision, speech recognition, and natural language processing. The clearly multidisciplinary nature of deep learning led to a call for papers for a special issue dedicated to learning deep architectures. [ABSTRACT FROM PUBLISHER]

Image retargeting techniques adjust images into different sizes and have attracted much attention recently. Objective quality assessment (OQA) of image retargeting results is often desired to automatically select the best results. Existing OQA methods train a model using some benchmarks (e.g., RetargetMe), in which subjective scores evaluated by users are provided. Observing that it is challenging even for human subjects to give consistent scores for retargeting results of different source images (diff-source-results), in this paper we propose a learning-based OQA method that trains a General Regression Neural Network (GRNN) model based on relative scores—which preserve the ranking—of retargeting results of the same source image (same-source-results). In particular, we develop a novel training scheme with provable convergence that learns a common base scalar for same-source-results. With this source specific offset, our computed scores not only preserve the ranking of subjective scores for same-source-results, but also provide a reference to compare the diff-source-results. We train and evaluate our GRNN model using human preference data collected in RetargetMe. We further introduce a subjective benchmark to evaluate the generalizability of different OQA methods. Experimental results demonstrate that our method outperforms ten representative OQA methods in ranking prediction and has better generalizability to different datasets. [ABSTRACT FROM AUTHOR]

Recent studies have shown that a Deep Convolutional Neural Network (DCNN) trained on a large image dataset can be used as a universal image descriptor and that doing so leads to impressive performance for a variety of image recognition tasks. Most of these studies adopt activations from a single DCNN layer, usually a fully-connected layer, as the image representation. In this paper, we proposed a novel way to extract image representations from two consecutive convolutional layers: one layer is used for local feature extraction and the other serves as guidance to pool the extracted features. By taking different viewpoints of convolutional layers, we further develop two schemes to realize this idea. The first directly uses convolutional layers from a DCNN. The second applies the pre-trained CNN on densely sampled image regions and treats the fully-connected activations of each image region as a convolutional layer's feature activations. We then train another convolutional layer on top of that as the pooling-guidance convolutional layer. By applying our method to three popular visual classification tasks, we find that our first scheme tends to perform better on applications which demand strong discrimination on lower-level visual patterns while the latter excels in cases that require discrimination on category-level patterns. Overall, the proposed method achieves superior performance over existing approaches for extracting image representations from a DCNN. In addition, we apply cross-layer pooling to the problem of image retrieval and propose schemes to reduce the computational cost. Experimental results suggest that the proposed method achieves promising results for the image retrieval task. [ABSTRACT FROM AUTHOR]

In this paper, we propose an end-to-end deep learning architecture that generates 3D triangular meshes from single color images. Restricted by the nature of prevalent deep learning techniques, the majority of previous works represent 3D shapes in volumes or point clouds. However, it is non-trivial to convert these representations to compact and ready-to-use mesh models. Unlike the existing methods, our network represents 3D shapes in meshes, which are essentially graphs and well suited for graph-based convolutional neural networks. Leveraging perceptual features extracted from an input image, our network produces the correct geometry by progressively deforming an ellipsoid. To make the whole deformation procedure stable, we adopt a coarse-to-fine strategy, and define various mesh/surface related losses to capture properties of various aspects, which benefits producing the visually appealing and physically accurate 3D geometry. In addition, our model by nature can be adapted to objects in specific domains, e.g., human faces, and be easily extended to learn per-vertex properties, e.g., color. Extensive experiments show that our method not only qualitatively produces the mesh model with better details, but also achieves the higher 3D shape estimation accuracy compared against the state-of-the-arts. [ABSTRACT FROM AUTHOR]

This paper proposes a new unsupervised domain adaptation approach called Collaborative and Adversarial Network (CAN), which uses the domain-collaborative and domain-adversarial learning strategies for training the neural network. The domain-collaborative learning strategy aims to learn domain specific feature representation to preserve the discriminability for the target domain, while the domain adversarial learning strategy aims to learn domain invariant feature representation to reduce the domain distribution mismatch between the source and target domains. We show that these two learning strategies can be uniformly formulated as domain classifier learning with positive or negative weights on the losses. We then design a collaborative and adversarial training scheme, which automatically learns domain specific representations from lower blocks in CNNs through collaborative learning and domain invariant representations from higher blocks through adversarial learning. Moreover, to further enhance the discriminability in the target domain, we propose Self-Paced CAN (SPCAN), which progressively selects pseudo-labeled target samples for re-training the classifiers. We employ a self-paced learning strategy such that we can select pseudo-labeled target samples in an easy-to-hard fashion. Additionally, we build upon the popular two-stream approach to extend our domain adaptation approach for more challenging video action recognition task, which additionally considers the cooperation between the RGB stream and the optical flow stream. We propose the Two-stream SPCAN (TS-SPCAN) method to select and reweight the pseudo labeled target samples of one stream (RGB/Flow) based on the information from the other stream (Flow/RGB) in a cooperative way. As a result, our TS-SPCAN model is able to exchange the information between the two streams. Comprehensive experiments on different benchmark datasets, Office-31, ImageCLEF-DA and VISDA-2017 for the object recognition task, and UCF101-10 and HMDB51-10 for the video action recognition task, show our newly proposed approaches achieve the state-of-the-art performance, which clearly demonstrates the effectiveness of our proposed approaches for unsupervised domain adaptation. [ABSTRACT FROM AUTHOR]

Recently, hyperbolic deep neural networks (HDNNs) have been gaining momentum as the deep representations in the hyperbolic space provide high fidelity embeddings with few dimensions, especially for data possessing hierarchical structure. Such a hyperbolic neural architecture is quickly extended to different scientific fields, including natural language processing, single-cell RNA-sequence analysis, graph embedding, financial analysis, and computer vision. The promising results demonstrate its superior capability, significant compactness of the model, and a substantially better physical interpretability than its counterpart in the euclidean space. To stimulate future research, this paper presents a comprehensive review of the literature around the neural components in the construction of HDNN, as well as the generalization of the leading deep approaches to the hyperbolic space. It also presents current applications of various tasks, together with insightful observations and identifying open questions and promising future directions. [ABSTRACT FROM AUTHOR]

This paper addresses the task of set prediction using deep feed-forward neural networks. A set is a collection of elements which is invariant under permutation and the size of a set is not fixed in advance. Many real-world problems, such as image tagging and object detection, have outputs that are naturally expressed as sets of entities. This creates a challenge for traditional deep neural networks which naturally deal with structured outputs such as vectors, matrices or tensors. We present a novel approach for learning to predict sets with unknown permutation and cardinality using deep neural networks. In our formulation we define a likelihood for a set distribution represented by a) two discrete distributions defining the set cardinally and permutation variables, and b) a joint distribution over set elements with a fixed cardinality. Depending on the problem under consideration, we define different training models for set prediction using deep neural networks. We demonstrate the validity of our set formulations on relevant vision problems such as: 1) multi-label image classification where we outperform the other competing methods on the PASCAL VOC and MS COCO datasets, 2) object detection, for which our formulation outperforms popular state-of-the-art detectors, and 3) a complex CAPTCHA test, where we observe that, surprisingly, our set-based network acquired the ability of mimicking arithmetics without any rules being coded. [ABSTRACT FROM AUTHOR]

During clinical practice, radiologists often use attributes, e.g., morphological and appearance characteristics of a lesion, to aid disease diagnosis. Effectively modeling attributes as well as all relationships involving attributes could boost the generalization ability and verifiability of medical image diagnosis algorithms. In this paper, we introduce a hybrid neuro-probabilistic reasoning algorithm for verifiable attribute-based medical image diagnosis. There are two parallel branches in our hybrid algorithm, a Bayesian network branch performing probabilistic causal relationship reasoning and a graph convolutional network branch performing more generic relational modeling and reasoning using a feature representation. Tight coupling between these two branches is achieved via a cross-network attention mechanism and the fusion of their classification results. We have successfully applied our hybrid reasoning algorithm to two challenging medical image diagnosis tasks. On the LIDC-IDRI benchmark dataset for benign-malignant classification of pulmonary nodules in CT images, our method achieves a new state-of-the-art accuracy of 95.36% and an AUC of 96.54%. Our method also achieves a 3.24% accuracy improvement on an in-house chest X-ray image dataset for tuberculosis diagnosis. Our ablation study indicates that our hybrid algorithm achieves a much better generalization performance than a pure neural network architecture under very limited training data. [ABSTRACT FROM AUTHOR]

Spiking neural networks (SNNs) have shown clear advantages over traditional artificial neural networks (ANNs) for low latency and high computational efficiency, due to their event-driven nature and sparse communication. However, the training of deep SNNs is not straightforward. In this paper, we propose a novel ANN-to-SNN conversion and layer-wise learning framework for rapid and efficient pattern recognition, which is referred to as progressive tandem learning. By studying the equivalence between ANNs and SNNs in the discrete representation space, a primitive network conversion method is introduced that takes full advantage of spike count to approximate the activation value of ANN neurons. To compensate for the approximation errors arising from the primitive network conversion, we further introduce a layer-wise learning method with an adaptive training scheduler to fine-tune the network weights. The progressive tandem learning framework also allows hardware constraints, such as limited weight precision and fan-in connections, to be progressively imposed during training. The SNNs thus trained have demonstrated remarkable classification and regression capabilities on large-scale object recognition, image reconstruction, and speech separation tasks, while requiring at least an order of magnitude reduced inference time and synaptic operations than other state-of-the-art SNN implementations. It, therefore, opens up a myriad of opportunities for pervasive mobile and embedded devices with a limited power budget. [ABSTRACT FROM AUTHOR]

Classification of 3D objects – the selection of a category in which each object belongs – is of great interest in the field of machine learning. Numerous researchers use deep neural networks to address this problem, altering the network architecture and representation of the 3D shape used as an input. To investigate the effectiveness of their approaches, we conduct an extensive survey of existing methods and identify common ideas by which we categorize them into a taxonomy. Second, we evaluate 11 selected classification networks on two 3D object datasets, extending the evaluation to a larger dataset on which most of the selected approaches have not been tested yet. For this, we provide a framework for converting shapes from common 3D mesh formats into formats native to each network, and for training and evaluating different classification approaches on this data. Despite being partially unable to reach the accuracies reported in the original papers, we compare the relative performance of the approaches as well as their performance when changing datasets as the only variable to provide valuable insights into performance on different kinds of data. We make our code available to simplify running training experiments with multiple neural networks with different prerequisites. [ABSTRACT FROM AUTHOR]

In this paper, we study the challenging problem of categorizing videos according to high-level semantics such as the existence of a particular human action or a complex event. Although extensive efforts have been devoted in recent years, most existing works combined multiple video features using simple fusion strategies and neglected the utilization of inter-class semantic relationships. This paper proposes a novel unified framework that jointly exploits the feature relationships and the class relationships for improved categorization performance. Specifically, these two types of relationships are estimated and utilized by imposing regularizations in the learning process of a deep neural network (DNN). Through arming the DNN with better capability of harnessing both the feature and the class relationships, the proposed regularized DNN (rDNN) is more suitable for modeling video semantics. We show that rDNN produces better performance over several state-of-the-art approaches. Competitive results are reported on the well-known Hollywood2 and Columbia Consumer Video benchmarks. In addition, to stimulate future research on large scale video categorization, we collect and release a new benchmark dataset, called FCVID, which contains 91,223 Internet videos and 239 manually annotated categories. [ABSTRACT FROM PUBLISHER]

Spherical images or videos, as typical non-euclidean data, are usually stored in the form of 2D panoramas obtained through an equirectangular projection, which is neither equal area nor conformal. The distortion caused by the projection limits the performance of vanilla Deep Neural Networks (DNNs) designed for traditional euclidean data. In this paper, we design a novel Spherical Deep Neural Network (DNN) to deal with the distortion caused by the equirectangular projection. Specifically, we customize a set of components, including a spherical convolution, a spherical pooling, a spherical ConvLSTM cell and a spherical MSE loss, as the replacements of their counterparts in vanilla DNNs for spherical data. The core idea is to change the identical behavior of the conventional operations in vanilla DNNs across different feature patches so that they will be adjusted to the distortion caused by the variance of sampling rate among different feature patches. We demonstrate the effectiveness of our Spherical DNNs for saliency detection and gaze estimation in $360^\circ$ 360 ∘ videos. For saliency detection, we take the temporal coherence of an observer’s viewing process into consideration and propose to use a Spherical U-Net and a Spherical ConvLSTM to predict the saliency maps for each frame sequentially. As for gaze prediction, we propose to leverage a Spherical Encoder Module to extract spatial panoramic features, then we combine them with the gaze trajectory feature extracted by an LSTM for future gaze prediction. To facilitate the study of the $360^\circ$ 360 ∘ videos saliency detection, we further construct a large-scale $360^\circ$ 360 ∘ video saliency detection dataset that consists of 104 $360^\circ$ 360 ∘ videos viewed by 20+ human subjects. Comprehensive experiments validate the effectiveness of our proposed Spherical DNNs for 360 $^\circ$ ∘ handwritten digit classification and sport classification, saliency detection and gaze tracking in $360^\circ$ 360 ∘ videos. We also visualize the regions contributing to the classification decisions in our proposed Spherical DNNs via the Grad-CAM technique in the classification task, and the results show that our Spherical DNNs constantly leverage reasonable and important regions for decision making, regardless the large distortions. All codes and dataset are available on https://github.com/svip-lab/SphericalDNNs. [ABSTRACT FROM AUTHOR]

The class of random features is one of the most popular techniques to speed up kernel methods in large-scale problems. Related works have been recognized by the NeurIPS Test-of-Time award in 2017 and the ICML Best Paper Finalist in 2019. The body of work on random features has grown rapidly, and hence it is desirable to have a comprehensive overview on this topic explaining the connections among various algorithms and theoretical results. In this survey, we systematically review the work on random features from the past ten years. First, the motivations, characteristics and contributions of representative random features based algorithms are summarized according to their sampling schemes, learning procedures, variance reduction properties and how they exploit training data. Second, we review theoretical results that center around the following key question: how many random features are needed to ensure a high approximation quality or no loss in the empirical/expected risks of the learned estimator. Third, we provide a comprehensive evaluation of popular random features based algorithms on several large-scale benchmark datasets and discuss their approximation quality and prediction performance for classification. Last, we discuss the relationship between random features and modern over-parameterized deep neural networks (DNNs), including the use of high dimensional random features in the analysis of DNNs as well as the gaps between current theoretical and empirical results. This survey may serve as a gentle introduction to this topic, and as a users’ guide for practitioners interested in applying the representative algorithms and understanding theoretical results under various technical assumptions. We hope that this survey will facilitate discussion on the open problems in this topic, and more importantly, shed light on future research directions. Due to the page limit, we suggest the readers refer to the full version of this survey https://arxiv.org/abs/2004.11154. [ABSTRACT FROM AUTHOR]

Error disagreement-based active learning (AL) selects the data that maximally update the error of a classification hypothesis. However, poor human supervision (e.g., few labels, improper classifier parameters) may weaken or clutter this update; moreover, the computational cost of performing a greedy search to estimate the errors using a deep neural network is intolerable. In this paper, a novel disagreement coefficient based on distribution, not error, provides a tighter bound on label complexity, which further guarantees its generalization in hyperbolic space. The focal points derived from the squared Lorentzian distance, present more effective hyperbolic representations on aspherical distribution from geometry, replacing the typical euclidean, kernelized, and Poincaré centroids. Experiments on different deep AL tasks show that, the focal representation adopted in a tree-likeliness splitting, significantly performs better than typical baselines of centroid representations and error disagreement, and state-of-the-art neural network architectures-based AL, dramatically accelerating the learning process. [ABSTRACT FROM AUTHOR]

With substantial amount of time, resources and human (team) efforts invested to explore and develop successful deep neural networks (DNN), there emerges an urgent need to protect these inventions from being illegally copied, redistributed, or abused without respecting the intellectual properties of legitimate owners. Following recent progresses along this line, we investigate a number of watermark-based DNN ownership verification methods in the face of ambiguity attacks, which aim to cast doubts on the ownership verification by forging counterfeit watermarks. It is shown that ambiguity attacks pose serious threats to existing DNN watermarking methods. As remedies to the above-mentioned loophole, this paper proposes novel passport-based DNN ownership verification schemes which are both robust to network modifications and resilient to ambiguity attacks. The gist of embedding digital passports is to design and train DNN models in a way such that, the DNN inference performance of an original task will be significantly deteriorated due to forged passports. In other words, genuine passports are not only verified by looking for the predefined signatures, but also reasserted by the unyielding DNN model inference performances. Extensive experimental results justify the effectiveness of the proposed passport-based DNN ownership verification schemes. Code is available at https://github.com/kamwoh/DeepIPR. [ABSTRACT FROM AUTHOR]

It is appealing but challenging to achieve real-time deep neural network (DNN) inference on mobile devices, because even the powerful modern mobile devices are considered as “resource-constrained” when executing large-scale DNNs. It necessitates the sparse model inference via weight pruning, i.e., DNN weight sparsity, and it is desirable to design a new DNN weight sparsity scheme that can facilitate real-time inference on mobile devices while preserving a high sparse model accuracy. This paper designs a novel mobile inference acceleration framework GRIM that is General to both convolutional neural networks (CNNs) and recurrent neural networks (RNNs) and that achieves Real-time execution and high accuracy, leveraging fine-grained structured sparse model Inference and compiler optimizations for Mobiles. We start by proposing a new fine-grained structured sparsity scheme through the Block-based Column-Row (BCR) pruning. Based on this new fine-grained structured sparsity, our GRIM framework consists of two parts: (a) the compiler optimization and code generation for real-time mobile inference; and (b) the BCR pruning optimizations for determining pruning hyperparameters and performing weight pruning. We compare GRIM with Alibaba MNN, TVM, TensorFlow-Lite, a sparse implementation based on CSR, PatDNN, and ESE (a representative FPGA inference acceleration framework for RNNs), and achieve up to $14.08\times$ 14. 08 × speedup. [ABSTRACT FROM AUTHOR]

Action segmentation is the task of predicting the actions for each frame of a video. As obtaining the full annotation of videos for action segmentation is expensive, weakly supervised approaches that can learn only from transcripts are appealing. In this paper, we propose a novel end-to-end approach for weakly supervised action segmentation based on a two-branch neural network. The two branches of our network predict two redundant but different representations for action segmentation and we propose a novel mutual consistency (MuCon) loss that enforces the consistency of the two redundant representations. Using the MuCon loss together with a loss for transcript prediction, our proposed approach achieves the accuracy of state-of-the-art approaches while being 14 times faster to train and 20 times faster during inference. The MuCon loss proves beneficial even in the fully supervised setting. [ABSTRACT FROM AUTHOR]

Current multi-object tracking and segmentation (MOTS) methods follow the tracking-by-detection paradigm and adopt 2D or 3D convolutions to extract instance embeddings for instance association. However, due to the large receptive field of deep convolutional neural networks, the foreground areas of the current instance and the surrounding areas containing the nearby instances or environments are usually mixed up in the learned instance embeddings, resulting in ambiguities in tracking. In this paper, we propose a highly effective method for learning instance embeddings based on segments by converting the compact image representation to un-ordered 2D point cloud representation. In this way, the non-overlapping nature of instance segments can be fully exploited by strictly separating the foreground point cloud and the background point cloud. Moreover, multiple informative data modalities are formulated as point-wise representations to enrich point-wise features. For each instance, the embedding is learned on the foreground 2D point cloud, the environment 2D point cloud, and the smallest circumscribed bounding box. Then, similarities between instance embeddings are measured for the inter-frame association. In addition, to enable the practical utility of MOTS, we modify the one-stage instance segmentation method SpatialEmbedding for instance segmentation. The resulting efficient and effective framework, named PointTrackV2, outperforms all the state-of-the-art methods including 3D tracking methods by large margins (4.8 percent higher sMOTSA for pedestrians over MOTSFusion) with the near real-time speed (20 FPS evaluated on a single 2080Ti). Extensive evaluations on three datasets demonstrate both the effectiveness and efficiency of our method. Furthermore, as crowded scenes for cars are insufficient in current MOTS datasets, we provide a more challenging dataset named APOLLO MOTS with a much higher instance density. [ABSTRACT FROM AUTHOR]

Handwritten signature verification is a challenging task because signatures of a writer may be skillfully imitated by a forger. As skilled forgeries are generally difficult to acquire for training, in this paper, we propose a deep learning-based dynamic signature verification framework, SynSig2Vec, to address the skilled forgery attack without training with any skilled forgeries. Specifically, SynSig2Vec consists of a novel learning-by-synthesis method for training and a 1D convolutional neural network model, called Sig2Vec, for signature representation extraction. The learning-by-synthesis method first applies the Sigma Lognormal model to synthesize signatures with different distortion levels for genuine template signatures, and then learns to rank these synthesized samples in a learnable representation space based on average precision optimization. The representation space is achieved by the proposed Sig2Vec model, which is designed to extract fixed-length representations from dynamic signatures of arbitrary lengths. Through this training method, the Sig2Vec model can extract extremely effective signature representations for verification. Our SynSig2Vec framework requires only genuine signatures for training, yet achieves state-of-the-art performance on the largest dynamic signature database to date, DeepSignDB, in both skilled forgery and random forgery scenarios. Source codes of SynSig2Vec will be available at https://github.com/LaiSongxuan/SynSig2Vec. [ABSTRACT FROM AUTHOR]

Reliably quantifying the confidence of deep neural classifiers is a challenging yet fundamental requirement for deploying such models in safety-critical applications. In this paper, we introduce a novel target criterion for model confidence, namely the true class probability (TCP). We show that TCP offers better properties for confidence estimation than standard maximum class probability (MCP). Since the true class is by essence unknown at test time, we propose to learn TCP criterion from data with an auxiliary model, introducing a specific learning scheme adapted to this context. We evaluate our approach on the task of failure prediction and of self-training with pseudo-labels for domain adaptation, which both necessitate effective confidence estimates. Extensive experiments are conducted for validating the relevance of the proposed approach in each task. We study various network architectures and experiment with small and large datasets for image classification and semantic segmentation. In every tested benchmark, our approach outperforms strong baselines. [ABSTRACT FROM AUTHOR]

Existing RGB-D salient object detection (SOD) models usually treat RGB and depth as independent information and design separate networks for feature extraction from each. Such schemes can easily be constrained by a limited amount of training data or over-reliance on an elaborately designed training process. Inspired by the observation that RGB and depth modalities actually present certain commonality in distinguishing salient objects, a novel joint learning and densely cooperative fusion (JL-DCF) architecture is designed to learn from both RGB and depth inputs through a shared network backbone, known as the Siamese architecture. In this paper, we propose two effective components: joint learning (JL), and densely cooperative fusion (DCF). The JL module provides robust saliency feature learning by exploiting cross-modal commonality via a Siamese network, while the DCF module is introduced for complementary feature discovery. Comprehensive experiments using five popular metrics show that the designed framework yields a robust RGB-D saliency detector with good generalization. As a result, JL-DCF significantly advances the state-of-the-art models by an average of $\sim 2.0\%$ ∼ 2. 0 % (max F-measure) across seven challenging datasets. In addition, we show that JL-DCF is readily applicable to other related multi-modal detection tasks, including RGB-T (thermal infrared) SOD and video SOD, achieving comparable or even better performance against state-of-the-art methods. We also link JL-DCF to the RGB-D semantic segmentation field, showing its capability of outperforming several semantic segmentation models on the task of RGB-D SOD. These facts further confirm that the proposed framework could offer a potential solution for various applications and provide more insight into the cross-modal complementarity task. [ABSTRACT FROM AUTHOR]

The light field (LF) reconstruction is mainly confronted with two challenges, large disparity and the non-Lambertian effect. Typical approaches either address the large disparity challenge using depth estimation followed by view synthesis or eschew explicit depth information to enable non-Lambertian rendering, but rarely solve both challenges in a unified framework. In this paper, we revisit the classic LF rendering framework to address both challenges by incorporating it with advanced deep learning techniques. First, we analytically show that the essential issue behind the large disparity and non-Lambertian challenges is the aliasing problem. Classic LF rendering approaches typically mitigate the aliasing with a reconstruction filter in the Fourier domain, which is, however, intractable to implement within a deep learning pipeline. Instead, we introduce an alternative framework to perform anti-aliasing reconstruction in the image domain and analytically show comparable efficacy on the aliasing issue. To explore the full potential, we then embed the anti-aliasing framework into a deep neural network through the design of an integrated architecture and trainable parameters. The network is trained through end-to-end optimization using a peculiar training set, including regular LFs and unstructured LFs. The proposed deep learning pipeline shows a substantial superiority in solving both the large disparity and the non-Lambertian challenges compared with other state-of-the-art approaches. In addition to the view interpolation for an LF, we also show that the proposed pipeline also benefits light field view extrapolation. [ABSTRACT FROM AUTHOR]

This paper generalizes the Attention in Attention (AiA) mechanism, in P. Fang et al., 2019 by employing explicit mapping in reproducing kernel Hilbert spaces to generate attention values of the input feature map. The AiA mechanism models the capacity of building inter-dependencies among the local and global features by the interaction of inner and outer attention modules. Besides a vanilla AiA module, termed linear attention with AiA, two non-linear counterparts, namely, second-order polynomial attention and Gaussian attention, are also proposed to utilize the non-linear properties of the input features explicitly, via the second-order polynomial kernel and Gaussian kernel approximation. The deep convolutional neural network, equipped with the proposed AiA blocks, is referred to as Attention in Attention Network (AiA-Net). The AiA-Net learns to extract a discriminative pedestrian representation, which combines complementary person appearance and corresponding part features. Extensive ablation studies verify the effectiveness of the AiA mechanism and the use of non-linear features hidden in the feature map for attention design. Furthermore, our approach outperforms current state-of-the-art by a considerable margin across a number of benchmarks. In addition, state-of-the-art performance is also achieved in the video person retrieval task with the assistance of the proposed AiA blocks. [ABSTRACT FROM AUTHOR]

Remarkable achievements have been obtained by deep neural networks in the last several years. However, the breakthrough in neural networks accuracy is always accompanied by explosive growth of computation and parameters, which leads to a severe limitation of model deployment. In this paper, we propose a novel knowledge distillation technique named self-distillation to address this problem. Self-distillation attaches several attention modules and shallow classifiers at different depths of neural networks and distills knowledge from the deepest classifier to the shallower classifiers. Different from the conventional knowledge distillation methods where the knowledge of the teacher model is transferred to another student model, self-distillation can be considered as knowledge transfer in the same model - from the deeper layers to the shallow layers. Moreover, the additional classifiers in self-distillation allow the neural network to work in a dynamic manner, which leads to a much higher acceleration. Experiments demonstrate that self-distillation has consistent and significant effectiveness on various neural networks and datasets. On average, 3.49 and 2.32 percent accuracy boost are observed on CIFAR100 and ImageNet. Besides, experiments show that self-distillation can be combined with other model compression methods, including knowledge distillation, pruning and lightweight model design. [ABSTRACT FROM AUTHOR]

We study network pruning which aims to remove redundant channels/kernels and hence speed up the inference of deep networks. Existing pruning methods either train from scratch with sparsity constraints or minimize the reconstruction error between the feature maps of the pre-trained models and the compressed ones. Both strategies suffer from some limitations: the former kind is computationally expensive and difficult to converge, while the latter kind optimizes the reconstruction error but ignores the discriminative power of channels. In this paper, we propose a simple-yet-effective method called discrimination-aware channel pruning (DCP) to choose the channels that actually contribute to the discriminative power. To this end, we first introduce additional discrimination-aware losses into the network to increase the discriminative power of the intermediate layers. Next, we select the most discriminative channels for each layer by considering the discrimination-aware loss and the reconstruction error, simultaneously. We then formulate channel pruning as a sparsity-inducing optimization problem with a convex objective and propose a greedy algorithm to solve the resultant problem. Note that a channel (3D tensor) often consists of a set of kernels (each with a 2D matrix). Besides the redundancy in channels, some kernels in a channel may also be redundant and fail to contribute to the discriminative power of the network, resulting in kernel level redundancy. To solve this issue, we propose a discrimination-aware kernel pruning (DKP) method to further compress deep networks by removing redundant kernels. To avoid manually determining the pruning rate for each layer, we propose two adaptive stopping conditions to automatically determine the number of selected channels/kernels. The proposed adaptive stopping conditions tend to yield more efficient models with better performance in practice. Extensive experiments on both image classification and face recognition demonstrate the effectiveness of our methods. For example, on ILSVRC-12, the resultant ResNet-50 model with 30 percent reduction of channels even outperforms the baseline model by 0.36 percent in terms of Top-1 accuracy. We also deploy the pruned models on a smartphone (equipped with a Qualcomm Snapdragon 845 processor). The pruned MobileNetV1 and MobileNetV2 achieve 1.93× and 1.42× inference acceleration on the mobile device, respectively, with negligible performance degradation. The source code and the pre-trained models are available at https://github.com/SCUT-AILab/DCP. [ABSTRACT FROM AUTHOR]

Stochastic optimization algorithms have been popular for training deep neural networks. Recently, there emerges a new approach of learning-based optimizer, which has achieved promising performance for training neural networks. However, these black-box learning-based optimizers do not fully take advantage of the experience in human-designed optimizers and heavily rely on learning from meta-training tasks, therefore have limited generalization ability. In this paper, we propose a novel optimizer, dubbed as Variational HyperAdam, which is based on a parametric generalized Adam algorithm, i.e., HyperAdam, in a variational framework. With Variational HyperAdam as optimizer for training neural network, the parameter update vector of the neural network at each training step is considered as random variable, whose approximate posterior distribution given the training data and current network parameter vector is predicted by Variational HyperAdam. The parameter update vector for network training is sampled from this approximate posterior distribution. Specifically, in Variational HyperAdam, we design a learnable generalized Adam algorithm for estimating expectation, paired with a VarBlock for estimating the variance of the approximate posterior distribution of parameter update vector. The Variational HyperAdam is learned in a meta-learning approach with meta-training loss derived by variational inference. Experiments verify that the learned Variational HyperAdam achieved state-of-the-art network training performance for various types of networks on different datasets, such as multilayer perceptron, CNN, LSTM and ResNet. [ABSTRACT FROM AUTHOR]

Deblurring images captured in dynamic scenes is challenging as the motion blurs are spatially varying caused by camera shakes and object movements. In this paper, we propose a spatially varying neural network to deblur dynamic scenes. The proposed model is composed of three deep convolutional neural networks (CNNs) and a recurrent neural network (RNN). The RNN is used as a deconvolution operator on feature maps extracted from the input image by one of the CNNs. Another CNN is used to learn the spatially varying weights for the RNN. As a result, the RNN is spatial-aware and can implicitly model the deblurring process with spatially varying kernels. To better exploit properties of the spatially varying RNN, we develop both one-dimensional and two-dimensional RNNs for deblurring. The third component, based on a CNN, reconstructs the final deblurred feature maps into a restored image. In addition, the whole network is end-to-end trainable. Quantitative and qualitative evaluations on benchmark datasets demonstrate that the proposed method performs favorably against the state-of-the-art deblurring algorithms. [ABSTRACT FROM AUTHOR]

The performance of distance-based classifiers heavily depends on the underlying distance metric, so it is valuable to learn a suitable metric from the data. To address the problem of multimodality, it is desirable to learn local metrics. In this short paper, we define a new intuitive distance with local metrics and influential regions, and subsequently propose a novel local metric learning algorithm called LMLIR for distance-based classification. Our key intuition is to partition the metric space into influential regions and a background region, and then regulate the effectiveness of each local metric to be within the related influential regions. We learn multiple local metrics and influential regions to reduce the empirical hinge loss, and regularize the parameters on the basis of a resultant learning bound. Encouraging experimental results are obtained from various public and popular data sets. [ABSTRACT FROM AUTHOR]

Fine-grained classification describes the automated recognition of visually similar object categories like birds species. Previous works were usually based on explicit pose normalization, i.e., the detection and description of object parts. However, recent models based on a final global average or bilinear pooling have achieved a comparable accuracy without this concept. In this paper, we analyze the advantages of these approaches over generic CNNs and explicit pose normalization approaches. We also show how they can achieve an implicit normalization of the object pose. A novel visualization technique called activation flow is introduced to investigate limitations in pose handling in traditional CNNs like AlexNet and VGG. Afterward, we present and compare the explicit pose normalization approach neural activation constellations and a generalized framework for the final global average and bilinear pooling called $\alpha$ α -pooling. We observe that the latter often achieves a higher accuracy improving common CNN models by up to 22.9 percent, but lacks the interpretability of the explicit approaches. We present a visualization approach for understanding and analyzing predictions of the model to address this issue. Furthermore, we show that our approaches for fine-grained recognition are beneficial for other fields like action recognition. [ABSTRACT FROM AUTHOR]

Most object detectors contain two important components: a feature extractor and an object classifier. The feature extractor has rapidly evolved with significant research efforts leading to better deep convolutional architectures. The object classifier, however, has not received much attention and many recent systems (like SPPnet and Fast/Faster R-CNN) use simple multi-layer perceptrons. This paper demonstrates that carefully designing deep networks for object classification is just as important. We experiment with region-wise classifier networks that use shared, region-independent convolutional features. We call them “Networks on Convolutional feature maps” (NoCs). We discover that aside from deep feature maps, a deep and convolutional per-region classifier is of particular importance for object detection, whereas latest superior image classification models (such as ResNets and GoogLeNets) do not directly lead to good detection accuracy without using such a per-region classifier. We show by experiments that despite the effective ResNets and Faster R-CNN systems, the design of NoCs is an essential element for the 1st-place winning entries in ImageNet and MS COCO challenges 2015. [ABSTRACT FROM PUBLISHER]

Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which only a few labeled samples are available. As deep neural networks (DNNs) tend to overfit using a few samples only, typical meta-learning models use shallow neural networks, thus limiting its effectiveness. In order to achieve top performance, some recent works tried to use the DNNs pre-trained on large-scale datasets but mostly in straight-forward manners, e.g., (1) taking their weights as a warm start of meta-training, and (2) freezing their convolutional layers as the feature extractor of base-learners. In this paper, we propose a novel approach called meta-transfer learning (MTL), which learns to transfer the weights of a deep NN for few-shot learning tasks. Specifically, meta refers to training multiple tasks, and transfer is achieved by learning scaling and shifting functions of DNN weights (and biases) for each task. To further boost the learning efficiency of MTL, we introduce the hard task (HT) meta-batch scheme as an effective learning curriculum of few-shot classification tasks. We conduct experiments for five-class few-shot classification tasks on three challenging benchmarks, miniImageNet, tieredImageNet, and Fewshot-CIFAR100 (FC100), in both supervised and semi-supervised settings. Extensive comparisons to related works validate that our MTL approach trained with the proposed HT meta-batch scheme achieves top performance. An ablation study also shows that both components contribute to fast convergence and high accuracy. [ABSTRACT FROM AUTHOR]

Many real–world domains involve information naturally represented by graphs, where nodes denote basic patterns while edges stand for relationships among them. The graph neural network (GNN) is a machine learning model capable of directly managing graph–structured data. In the original framework, GNNs are inductively trained, adapting their parameters based on a supervised learning environment. However, GNNs can also take advantage of transductive learning, thanks to the natural way they make information flow and spread across the graph, using relationships among patterns. In this paper, we propose a mixed inductive–transductive GNN model, study its properties and introduce an experimental strategy that allows us to understand and distinguish the role of inductive and transductive learning. The preliminary experimental results show interesting properties for the mixed model, highlighting how the peculiarities of the problems and the data can impact on the two learning strategies. [ABSTRACT FROM AUTHOR]

In this paper, a novel convolutional neural network (CNN)-based framework is developed for light field reconstruction from a sparse set of views. We indicate that the reconstruction can be efficiently modeled as angular restoration on an epipolar plane image (EPI). The main problem in direct reconstruction on the EPI involves an information asymmetry between the spatial and angular dimensions, where the detailed portion in the angular dimensions is damaged by undersampling. Directly upsampling or super-resolving the light field in the angular dimensions causes ghosting effects. To suppress these ghosting effects, we contribute a novel "blur-restoration-deblur" framework. First, the "blur" step is applied to extract the low-frequency components of the light field in the spatial dimensions by convolving each EPI slice with a selected blur kernel. Then, the "restoration" step is implemented by a CNN, which is trained to restore the angular details of the EPI. Finally, we use a non-blind "deblur" operation to recover the spatial high frequencies suppressed by the EPI blur. We evaluate our approach on several datasets, including synthetic scenes, real-world scenes and challenging microscope light field data. We demonstrate the high performance and robustness of the proposed framework compared with state-of-the-art algorithms. We further show extended applications, including depth enhancement and interpolation for unstructured input. More importantly, a novel rendering approach is presented by combining the proposed framework and depth information to handle large disparities. [ABSTRACT FROM AUTHOR]

In this paper, we propose a two-stream transformer networks (TSTN) approach for video-based face alignment. Unlike conventional image-based face alignment approaches which cannot explicitly model the temporal dependency in videos and motivated by the fact that consistent movements of facial landmarks usually occur across consecutive frames, our TSTN aims to capture the complementary information of both the spatial appearance on still frames and the temporal consistency information across frames. To achieve this, we develop a two-stream architecture, which decomposes the video-based face alignment into spatial and temporal streams accordingly. Specifically, the spatial stream aims to transform the facial image to the landmark positions by preserving the holistic facial shape structure. Accordingly, the temporal stream encodes the video input as active appearance codes, where the temporal consistency information across frames is captured to help shape refinements. Experimental results on the benchmarking video-based face alignment datasets show very competitive performance of our method in comparisons to the state-of-the-arts. [ABSTRACT FROM AUTHOR]

The rapid development of deep neural networks (DNNs) in recent years can be attributed to the various techniques that address gradient explosion and vanishing. In order to understand the principle behind these techniques and develop new methods, plenty of metrics have been proposed to identify networks that are free of gradient explosion and vanishing. However, due to the diversity of network components and complex serial-parallel hybrid connections in modern DNNs, the evaluation of existing metrics usually requires strong assumptions, complex statistical analysis, or has limited application fields, which constraints their spread in the community. In this paper, inspired by the Gradient Norm Equality and dynamical isometry, we first propose a novel metric called Block Dynamical Isometry, which measures the change of gradient norm in individual blocks. Because our Block Dynamical Isometry is norm-based, its evaluation needs weaker assumptions compared with the original dynamical isometry. To mitigate challenging derivation, we propose a highly modularized statistical framework based on free probability. Our framework includes several key theorems to handle complex serial-parallel hybrid connections and a library to cover the diversity of network components. Besides, several sufficient conditions for prerequisites are provided. Powered by our metric and framework, we analyze extensive initialization, normalization, and network structures. We find that our Block Dynamical Isometry is a universal philosophy behind them. Then, we improve some existing methods based on our analysis, including an activation function selection strategy for initialization techniques, a new configuration for weight normalization, a depth-aware way to derive coefficients in SeLU, and initialization/weight normalization in DenseNet. Moreover, we propose a novel normalization technique named second moment normalization, which has 30 percent fewer computation overhead than batch normalization without accuracy loss and has better performance under micro batch size. Last but not least, our conclusions and methods are evidenced by extensive experiments on multiple models over CIFAR-10 and ImageNet. [ABSTRACT FROM AUTHOR]

In this paper, we present a method to mine object-part patterns from conv-layers of a pre-trained convolutional neural network (CNN). The mined object-part patterns are organized by an And-Or graph (AOG). This interpretable AOG representation consists of a four-layer semantic hierarchy, i.e., semantic parts, part templates, latent patterns, and neural units. The AOG associates each object part with certain neural units in feature maps of conv-layers. The AOG is constructed with very few annotations (e.g., 3–20) of object parts. We develop a question-answering (QA) method that uses active human-computer communications to mine patterns from a pre-trained CNN, in order to explain features in conv-layers incrementally. During the learning process, our QA method uses the current AOG for part localization. The QA method actively identifies objects, whose feature maps cannot be explained by the AOG. Then, our method asks people to annotate parts on the unexplained objects, and uses answers to discover CNN patterns corresponding to newly labeled parts. In this way, our method gradually grows new branches and refines existing branches on the AOG to semanticize CNN representations. In experiments, our method exhibited a high learning efficiency. Our method used about $1/6$ 1 / 6 – $1/3$ 1 / 3 of the part annotations for training, but achieved similar or better part-localization performance than fast-RCNN methods. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel end-to-end deep neural network model for omnidirectional depth estimation from a wide-baseline multi-view stereo setup. The images captured with ultra-wide field-of-view cameras on an omnidirectional rig are processed by the feature extraction module, and then the deep feature maps are warped onto the concentric spheres swept through all candidate depths using the calibrated camera parameters. The 3D encoder-decoder block takes the aligned feature volume to produce an omnidirectional depth estimate with regularization on uncertain regions utilizing the global context information. For more accurate depth estimation we also propose an uncertainty prior guidance in two ways: depth map filtering and guiding regularization. In addition, we present large-scale synthetic datasets for training and testing omnidirectional multi-view stereo algorithms. Our datasets consist of 13K ground-truth depth maps and 53K fisheye images in four orthogonal directions with various objects and environments. Experimental results show that the proposed method generates excellent results in both synthetic and real-world environments, and it outperforms the prior art and the omnidirectional versions of the state-of-the-art conventional stereo algorithms. [ABSTRACT FROM AUTHOR]