Search

This paper studies the allocation of shared resources between vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) links in vehicle-to-everything (V2X) communications. In existing algorithms, dynamic vehicular environments and quantization of continuous power become the bottlenecks for providing an effective and timely resource allocation policy. In this paper, we develop two algorithms to deal with these difficulties. First, we propose a deep reinforcement learning (DRL)-based resource allocation algorithm to improve the performance of both V2I and V2V links. Specifically, the algorithm uses deep Q-network (DQN) to solve the sub-band assignment and deep deterministic policy-gradient (DDPG) to solve the continuous power allocation problem. Second, we propose a meta-based DRL algorithm to enhance the fast adaptability of the resource allocation policy in the dynamic environment. Numerical results demonstrate that the proposed DRL-based algorithm can significantly improve the performance compared to the DQN-based algorithm that quantizes continuous power. In addition, the proposed meta-based DRL algorithm can achieve the required fast adaptation in the new environment with limited experiences. [ABSTRACT FROM AUTHOR]

The aim of this paper is to provide a comprehensive overview of the MICCAI 2020 AutoImplant Challenge. The approaches and publications submitted and accepted within the challenge will be summarized and reported, highlighting common algorithmic trends and algorithmic diversity. Furthermore, the evaluation results will be presented, compared and discussed in regard to the challenge aim: seeking for low cost, fast and fully automated solutions for cranial implant design. Based on feedback from collaborating neurosurgeons, this paper concludes by stating open issues and post-challenge requirements for intra-operative use. The codes can be found at https://github.com/Jianningli/tmi. [ABSTRACT FROM AUTHOR]

Scene flow represents the 3D motion of every point in the dynamic environments. Like the optical flow that represents the motion of pixels in 2D images, 3D motion representation of scene flow benefits many applications, such as autonomous driving and service robot. This paper studies the problem of scene flow estimation from two consecutive 3D point clouds. In this paper, a novel hierarchical neural network with double attention is proposed for learning the correlation of point features in adjacent frames and refining scene flow from coarse to fine layer by layer. The proposed network has a new more-for-less hierarchical architecture. The more-for-less means that the number of input points is greater than the number of output points for scene flow estimation, which brings more input information and balances the precision and resource consumption. In this hierarchical architecture, scene flow of different levels is generated and supervised respectively. A novel attentive embedding module is introduced to aggregate the features of adjacent points using a double attention method in a patch-to-patch manner. The proper layers for flow embedding and flow supervision are carefully considered in our network designment. Experiments show that the proposed network outperforms the state-of-the-art performance of 3D scene flow estimation on the FlyingThings3D and KITTI Scene Flow 2015 datasets. We also apply the proposed network to the realistic LiDAR odometry task, which is a key problem in autonomous driving. The experiment results demonstrate that our proposed network can outperform the ICP-based method and shows good practical application ability. The source codes will be released on https://github.com/IRMVLab/HALFlow. [ABSTRACT FROM AUTHOR]

Face hallucination or super-resolution is a practical application of general image super-resolution which has been recently studied by many researchers. The challenge of good face hallucination comes from a variety of poses, illuminations, facial expressions, and other degradations. In many proposed methods, researchers resolve it by using a generative neural network to reduce the perceptual loss so we can generate a photo-realistic image. The problem is that researchers usually overlook the fidelity of the super-resolved image which could affect further facial image processing. Meanwhile, many CNN based approaches cascade multiple networks to extract facial prior information to improve super-resolution quality. Because of the end-to-end design, the details are missing for investigation. In this paper, we combine new techniques in convolutional neural network and random forests to a Hierarchical CNN based Random Forests (HCRF) approach for face super-resolution in a coarse-to-fine manner. In the proposed approach, we focus on a general approach that can handle facial images with various conditions without pre-processing. To the best of our knowledge, this is the first paper that combines the advantages of deep learning with random forests for face super-resolution. To achieve superior performance, we propose two novel CNN models for coarse facial image super-resolution and segmentation and then apply new random forests to target on local facial features refinement making use of the segmentation results. Extensive benchmark experiments on subjective and objective evaluation show that HCRF can achieve comparable speed and competitive performance compared with state-of-the-art super-resolution approaches for very low-resolution images. [ABSTRACT FROM AUTHOR]

This paper focuses on the thorax disease classification problem in chest X-ray (CXR) images. Different from the generic image classification task, a robust and stable CXR image analysis system should consider the unique characteristics of CXR images. Particularly, it should be able to: 1) automatically focus on the disease-critical regions, which usually are of small sizes; 2) adaptively capture the intrinsic relationships among different disease features and utilize them to boost the multi-label disease recognition rates jointly. In this paper, we propose to learn discriminative features with a two-branch architecture, named ConsultNet, to achieve those two purposes simultaneously. ConsultNet consists of two components. First, an information bottleneck constrained feature selector extracts critical disease-specific features according to the feature importance. Second, a spatial-and-channel encoding based feature integrator enhances the latent semantic dependencies in the feature space. ConsultNet fuses these discriminative features to improve the performance of thorax disease classification in CXRs. Experiments conducted on the ChestX-ray14 and CheXpert dataset demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Deep learning models are sensitive to domain shift phenomena. A model trained on images from one domain cannot generalise well when tested on images from a different domain, despite capturing similar anatomical structures. It is mainly because the data distribution between the two domains is different. Moreover, creating annotation for every new modality is a tedious and time-consuming task, which also suffers from high inter- and intra- observer variability. Unsupervised domain adaptation (UDA) methods intend to reduce the gap between source and target domains by leveraging source domain labelled data to generate labels for the target domain. However, current state-of-the-art (SOTA) UDA methods demonstrate degraded performance when there is insufficient data in source and target domains. In this paper, we present a novel UDA method for multi-modal cardiac image segmentation. The proposed method is based on adversarial learning and adapts network features between source and target domain in different spaces. The paper introduces an end-to-end framework that integrates: a) entropy minimization, b) output feature space alignment and c) a novel point-cloud shape adaptation based on the latent features learned by the segmentation model. We validated our method on two cardiac datasets by adapting from the annotated source domain, bSSFP-MRI (balanced Steady-State Free Procession-MRI), to the unannotated target domain, LGE-MRI (Late-gadolinium enhance-MRI), for the multi-sequence dataset; and from MRI (source) to CT (target) for the cross-modality dataset. The results highlighted that by enforcing adversarial learning in different parts of the network, the proposed method delivered promising performance, compared to other SOTA methods. [ABSTRACT FROM AUTHOR]

For CNN-based visual action recognition, the accuracy may be increased if local key action regions are focused on. The task of self-attention is to focus on key features and ignore irrelevant information. So, self-attention is useful for action recognition. However, current self-attention methods usually ignore correlations among local feature vectors at spatial positions in CNN feature maps. In this paper, we propose an effective interaction-aware self-attention model which can extract information about the interactions between feature vectors to learn attention maps. Since the different layers in a network capture feature maps at different scales, we introduce a spatial pyramid with the feature maps at different layers for attention modeling. The multi-scale information is utilized to obtain more accurate attention scores. These attention scores are used to weight the local feature vectors of the feature maps and then calculate attentional feature maps. Since the number of feature maps input to the spatial pyramid attention layer is unrestricted, we easily extend this attention layer to a spatio-temporal version. Our model can be embedded in any general CNN to form a video-level end-to-end attention network for action recognition. Several methods are investigated to combine the RGB and flow streams to obtain accurate predictions of human actions. Experimental results show that our method achieves state-of-the-art results on the datasets UCF101, HMDB51, Kinetics-400, and untrimmed Charades. [ABSTRACT FROM AUTHOR]

With the unprecedented developments in deep learning, automatic segmentation of main abdominal organs seems to be a solved problem as state-of-the-art (SOTA) methods have achieved comparable results with inter-rater variability on many benchmark datasets. However, most of the existing abdominal datasets only contain single-center, single-phase, single-vendor, or single-disease cases, and it is unclear whether the excellent performance can generalize on diverse datasets. This paper presents a large and diverse abdominal CT organ segmentation dataset, termed AbdomenCT-1K, with more than 1000 (1K) CT scans from 12 medical centers, including multi-phase, multi-vendor, and multi-disease cases. Furthermore, we conduct a large-scale study for liver, kidney, spleen, and pancreas segmentation and reveal the unsolved segmentation problems of the SOTA methods, such as the limited generalization ability on distinct medical centers, phases, and unseen diseases. To advance the unsolved problems, we further build four organ segmentation benchmarks for fully supervised, semi-supervised, weakly supervised, and continual learning, which are currently challenging and active research topics. Accordingly, we develop a simple and effective method for each benchmark, which can be used as out-of-the-box methods and strong baselines. We believe the AbdomenCT-1K dataset will promote future in-depth research towards clinical applicable abdominal organ segmentation methods. [ABSTRACT FROM AUTHOR]

We consider the reconstruction problem of video snapshot compressive imaging (SCI), which captures high-speed videos using a low-speed 2D sensor (detector). The underlying principle of SCI is to modulate sequential high-speed frames with different masks and then these encoded frames are integrated into a snapshot on the sensor and thus the sensor can be of low-speed. On one hand, video SCI enjoys the advantages of low-bandwidth, low-power and low-cost. On the other hand, applying SCI to large-scale problems (HD or UHD videos) in our daily life is still challenging and one of the bottlenecks lies in the reconstruction algorithm. Existing algorithms are either too slow (iterative optimization algorithms) or not flexible to the encoding process (deep learning based end-to-end networks). In this paper, we develop fast and flexible algorithms for SCI based on the plug-and-play (PnP) framework. In addition to the PnP-ADMM method, we further propose the PnP-GAP (generalized alternating projection) algorithm with a lower computational workload. We first employ the image deep denoising priors to show that PnP can recover a UHD color video with 30 frames from a snapshot measurement. Since videos have strong temporal correlation, by employing the video deep denoising priors, we achieve a significant improvement in the results. Furthermore, we extend the proposed PnP algorithms to the color SCI system using mosaic sensors, where each pixel only captures the red, green or blue channels. A joint reconstruction and demosaicing paradigm is developed for flexible and high quality reconstruction of color video SCI systems. Extensive results on both simulation and real datasets verify the superiority of our proposed algorithm. [ABSTRACT FROM AUTHOR]

One of the most prominent attributes of Neural Networks (NNs) constitutes their capability of learning to extract robust and descriptive features from high dimensional data, like images. Hence, such an ability renders their exploitation as feature extractors particularly frequent in an abundance of modern reasoning systems. Their application scope mainly includes complex cascade tasks, like multi-modal recognition and deep Reinforcement Learning (RL). However, NNs induce implicit biases that are difficult to avoid or to deal with and are not met in traditional image descriptors. Moreover, the lack of knowledge for describing the intra-layer properties -and thus their general behavior- restricts the further applicability of the extracted features. With the paper at hand, a novel way of visualizing and understanding the vector space before the NNs’ output layer is presented, aiming to enlighten the deep feature vectors’ properties under classification tasks. Main attention is paid to the nature of overfitting in the feature space and its adverse effect on further exploitation. We present the findings that can be derived from our model’s formulation and we evaluate them on realistic recognition scenarios, proving its prominence by improving the obtained results. [ABSTRACT FROM AUTHOR]

Measuring contact friction in soft-bodies usually requires a specialised physics bench and a tedious acquisition protocol. This makes the prospect of a purely non-invasive, video-based measurement technique particularly attractive. Previous works have shown that such a video-based estimation is feasible for material parameters using deep learning, but this has never been applied to the friction estimation problem which results in even more subtle visual variations. Because acquiring a large dataset for this problem is impractical, generating it from simulation is the obvious alternative. However, this requires the use of a frictional contact simulator whose results are not only visually plausible, but physically-correct enough to match observations made at the macroscopic scale. In this paper, which is an extended version of our former work A. H. Rasheed, V. Romero, F. Bertails-Descoubes, S. Wuhrer, J.-S. Franco, and A Lazarus, “Learning to measure the static friction coefficient in cloth contact,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., 2020, pp. 9909–9918, we propose to our knowledge the first non-invasive measurement network and adjoining synthetic training dataset for estimating cloth friction at contact, for both cloth-hard body and cloth-cloth contacts. To this end we build a protocol for validating and calibrating a state-of-the-art frictional contact simulator, in order to produce a reliable dataset. We furthermore show that without our careful calibration procedure, the training fails to provide accurate estimation results on real data. We present extensive results on a large acquired test set of several hundred real video sequences of cloth in friction, which validates the proposed protocol and its accuracy. [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]

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]

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]

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]

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]

Deep learning based models have excelled in many computer vision tasks and appear to surpass humans’ performance. However, these models require an avalanche of expensive human labeled training data and many iterations to train their large number of parameters. This severely limits their scalability to the real-world long-tail distributed categories, some of which are with a large number of instances, but with only a few manually annotated. Learning from such extremely limited labeled examples is known as Few-Shot Learning (FSL). Different to prior arts that leverage meta-learning or data augmentation strategies to alleviate this extremely data-scarce problem, this paper presents a statistical approach, dubbed Instance Credibility Inference (ICI) to exploit the support of unlabeled instances for few-shot visual recognition. Typically, we repurpose the self-taught learning paradigm to predict pseudo-labels of unlabeled instances with an initial classifier trained from the few shot and then select the most confident ones to augment the training set to re-train the classifier. This is achieved by constructing a (Generalized) Linear Model (LM/GLM) with incidental parameters to model the mapping from (un-)labeled features to their (pseudo-)labels, in which the sparsity of the incidental parameters indicates the credibility of the corresponding pseudo-labeled instance. We rank the credibility of pseudo-labeled instances along the regularization path of their corresponding incidental parameters, and the most trustworthy pseudo-labeled examples are preserved as the augmented labeled instances. This process is repeated until all the unlabeled samples are included in the expanded training set. Theoretically, under the conditions of restricted eigenvalue, irrepresentability, and large error, our approach is guaranteed to collect all the correctly-predicted pseudo-labeled instances from the noisy pseudo-labeled set. Extensive experiments under two few-shot settings show the effectiveness of our approach on four widely used few-shot visual recognition benchmark datasets including miniImageNet, tieredImageNet, CIFAR-FS, and CUB. Code and models are released at https://github.com/Yikai-Wang/ICI-FSL. [ABSTRACT FROM AUTHOR]

Accurate and automatic segmentation of three-dimensional (3D) individual teeth from cone-beam computerized tomography (CBCT) images is a challenging problem because of the difficulty in separating an individual tooth from adjacent teeth and its surrounding alveolar bone. Thus, this paper proposes a fully automated method of identifying and segmenting 3D individual teeth from dental CBCT images. The proposed method addresses the aforementioned difficulty by developing a deep learning-based hierarchical multi-step model. First, it automatically generates upper and lower jaws panoramic images to overcome the computational complexity caused by high-dimensional data and the curse of dimensionality associated with limited training dataset. The obtained 2D panoramic images are then used to identify 2D individual teeth and capture loose- and tight- regions of interest (ROIs) of 3D individual teeth. Finally, accurate 3D individual tooth segmentation is achieved using both loose and tight ROIs. Experimental results showed that the proposed method achieved an F1-score of 93.35 percent for tooth identification and a Dice similarity coefficient of 94.79 percent for individual 3D tooth segmentation. The results demonstrate that the proposed method provides an effective clinical and practical framework for digital dentistry. [ABSTRACT FROM AUTHOR]

Recent advances in video processing utilizing deep learning primitives achieved breakthroughs in fundamental problems in video analysis such as frame classification and object detection enabling an array of new applications. In this paper we study the problem of interactive declarative query processing on video streams. In particular we introduce a set of approximate filters to speed up queries that involve objects of specific type (e.g., cars, trucks, etc.) on video frames with associated spatial relationships among them (e.g., car left of truck). The resulting filters are able to assess quickly if the query predicates are true to proceed with further analysis of the frame or otherwise not consider the frame further avoiding costly object detection operations. We propose two classes of filters $IC$ I C and $OD$ O D , that adapt principles from deep image classification and object detection. The filters utilize extensible deep neural architectures and are easy to deploy and utilize. In addition, we propose statistical query processing techniques to process aggregate queries involving objects with spatial constraints on video streams and demonstrate experimentally the resulting increased accuracy on the resulting aggregate estimation. Finally, we introduce a framework based on extreme value theory to detect unexpected objects on video streams and experimentally demonstrate its utility. Combined these techniques constitute a robust set of video monitoring query processing techniques. We demonstrate that the application of the techniques proposed in conjunction with declarative queries on video streams can dramatically increase the frame processing rate and speed up query processing by at least two orders of magnitude. We present the results of a thorough experimental study utilizing benchmark video data sets at scale demonstrating the performance benefits and the practical relevance of our proposals. [ABSTRACT FROM AUTHOR]

This paper investigates the stochastic optimization problem focusing on developing scalable parallel algorithms for deep learning tasks. Our solution involves a reformation of the objective function for stochastic optimization in neural network models, along with a novel parallel computing strategy, coined the weighted aggregating stochastic gradient descent (WASGD). Following a theoretical analysis on the characteristics of the new objective function, WASGD introduces a decentralized weighted aggregating scheme based on the performance of local workers. Without any center variable, the new method automatically gauges the importance of local workers and accepts them by their contributions. Furthermore, we have developed an enhanced version of the method, WASGD+, by (1) implementing a designed sample order and (2) upgrading the weight evaluation function. To validate the new method, we benchmark our pipeline against several popular algorithms including the state-of-the-art deep neural network classifier training techniques (e.g., elastic averaging SGD). Comprehensive validation studies have been conducted on four classic datasets: CIFAR-100, CIFAR-10, Fashion-MNIST, and MNIST. Subsequent results have firmly validated the superiority of the WASGD scheme in accelerating the training of deep architecture. Better still, the enhanced version, WASGD+, is shown to be a significant improvement over its prototype. [ABSTRACT FROM AUTHOR]

The separation of the data capture and analysis in modern vision systems has led to a massive amount of data transfer between the end devices and cloud computers, resulting in long latency, slow response, and high power consumption. Efficient hardware architectures are under focused development to enable Artificial Intelligence (AI) at the resource-limited sensing devices. One of the most promising solutions is to enable Processing-in-Pixel (PIP) scheme. However, the conventional schemes suffer from the low fill-factor issue. This paper proposes a PIP based Complementary Metal-Oxide-Semiconductor (CMOS) sensor architecture, which allows convolution operation before the column readout circuit to significantly reduce the overall power consumption while improving the resource utilization of the succeeding deep learning accelerator. The simulation results show that the proposed architecture could support the computing efficiency up to 3.37 TOPS/W at the 8-bit weight configuration, which is four times as high as the conventional schemes after normalization. The transistors required for each pixel are only 3.5T, significantly improving the fill-factor. [ABSTRACT FROM AUTHOR]

Image captioning generates descriptions in a natural language for a given image. Due to its great potential for a wide range of applications, many deep learning based-methods have been proposed. The co-occurrence of words such as mouse and keyboard, constitutes commonsense knowledge, which is referred to as consensus. However, it is challenging to consider commonsense knowledge in producing captions that have rich, natural, and meaningful semantics. In this paper, a Vision-enhanced and Consensus-aware Transformer (VCT) is proposed to exploit both visual information and consensus knowledge for image captioning with three key components: a vision-enhanced encoder, consensus-aware knowledge representation generator, and consensus-aware decoder. The vision-enhanced encoder extends the vanilla self-attention module with a memory-based attention module and a visual perception module for learning better visual representation of an image. Specifically, the relationships between regions in an image and the image’s global context are leveraged with scene memory in the memory-based attention module. The visual perception module further enhances the correlation among neighboring tokens in both the spatial and channel-wise dimensions. To learn consensus-aware representations, a word correlation graph is constructed by computing the statistical co-occurrence between semantic concepts. Then consensus knowledge can be acquired using a graph convolutional network in the consensus-aware knowledge representation generator. Finally, such consensus knowledge is integrated into the consensus-aware decoder through consensus memory and a knowledge-based control module to produce a caption. Experimental results on two popular benchmark datasets (MSCOCO and Flickr30k) demonstrate that our proposed model achieves state-of-the-art performance. Extensive ablation studies also validate the effectiveness of each component. [ABSTRACT FROM AUTHOR]

Video grounding aims at localizing the temporal moment related to the given language description, which is very helpful to many cross-modal content understanding applications like visual question answering and sentence-video search. Existing approaches usually directly regress the temporal boundaries of an event described by a query sentence in the video sequence. This direct regression manner often encounters a large decision space due to diverse target events and variable video durations, leading to inaccurate localization as well as inefficient grounding. This paper presents an efficient framework termed from which to where to facilitate video grounding. The core idea is imitating the reading comprehension process to gradually narrow the decision space, in what we decompose the direct regression into two steps. The “which” step first roughly selects a candidate area by evaluating which video segment in the predefined set is closest to the ground truth. To this end, we formulate this step into a multi-choice reading comprehension problem and propose a criterion to select the best-matched segment. In this way, the excessive decision space is effectively reduced. The “where” step aims to precisely regress the temporal boundary of the selected video segment from the shrunk decision space. We thus introduce a triple-span representation for each candidate video segment to use the regional context for better boundary regression. The “which” and “where” steps can be combined into a unified framework and learned end-to-end, leading to an efficient video grounding system. Extensive experiments on Charades-STA, ActivityNet-Captions, and TACoS benchmarks clearly demonstrate the effectiveness of our framework. [ABSTRACT FROM AUTHOR]

In order to retain more feature information of local areas on a point cloud, local grouping and subsampling are the necessary data structuring steps in most hierarchical deep learning models. Due to the disorder nature of the points in a point cloud, the significant time cost may be consumed when grouping and subsampling the points, which consequently results in poor scalability. This paper proposes a fast data structuring method called PSNet (Point Structuring Net). PSNet transforms the spatial features of the points and matches them to the features of local areas in a point cloud. PSNet achieves grouping and sampling at the same time while the existing methods process sampling and grouping in two separate steps (such as using FPS plus kNN). PSNet performs feature transformation pointwise while the existing methods uses the spatial relationship among the points as the reference for grouping. Thanks to these features, PSNet has two important advantages: 1) the grouping and sampling results obtained by PSNet is stable and permutation invariant; and 2) PSNet can be easily parallelized. PSNet can replace the data structuring methods in the mainstream point cloud deep learning models in a plug-and-play manner. We have conducted extensive experiments. The results show that PSNet can improve the training and inference speed significantly while maintaining the model accuracy. [ABSTRACT FROM AUTHOR]

As a powerful statistical signal modeling technique, sparse representation has been widely used in various image restoration (IR) applications. The sparsity-based methods have achieved leading performance in the past few decades. However, in recent years it has been surpassed by other methods, especially the recent deep learning based methods. In this paper, we address the question that whether sparse representation can be competitive again. The way we answer this question is to redesign it with a deep architecture. To be specific, we propose an end-to-end deep architecture that follows the process of the sparse representation based IR. In particular, we learn a sparse convolutional dictionary to replace the traditional dictionary, and a convolutional neural network (CNN) denoising prior to replace the image prior. Through end-to-end training, the parameters in convolutional dictionary and CNN denoiser can be jointly optimized. Experimental results on several representative IR tasks, including image denoising, deblurring and super-resolution, demonstrate that the proposed deep network can achieve superior performance against state-of-the-art model-based and learning-based methods. [ABSTRACT FROM AUTHOR]

Models for image semantics understanding, such as deep learning (DL) models and mathematical models, are often trained on specific dataset or configured with specific parameters. When deploying such models on new tasks in a different test environment, it requires considerable effort to re-train the model or extensive expertise to tune the parameters. In this paper, we propose a smart reinforcement learning (RL) agent that could learn to tune parameters automatically to enhance model performance. The learning process is formulated as a generic control task for parameter adjustment, and applied to two use scenarios: (1) image attributes tuning to improve object detection performance on fixed DL model, and (2) parameter tuning of the mathematical model (Level Set) for image segmentation. We design a novel dynamic threshold mechanism in a multi-branch RL agent to effectively tune parameters of image qualities (for object detection) and Level Set models (for object segmentation). We conduct experiments on Pascal-VOC testing set, MS COCO validation set and a proprietary dataset of industrial components, where we achieve substantial improvement on object detection accuracy. We also perform experiments on the automatic parameter tuning of Level Set models. Results show that our method facilitates considerable performance improvement on public datasets compared with baseline method. [ABSTRACT FROM AUTHOR]

Modeling 3D visual saliency has received great attention due to the development of emerging 3D display technologies. Traditional methods relying on low-level features may not be efficient in interpreting 3D visual content from high-level semantic perspective. Despite numerous efforts dedicated to this area, existing 3D visual saliency detection methods do not necessarily excel in exploring the stereoscopic image saliency driven by the intra-view and inter-view dependencies among left and right views. In this paper, we propose a visual saliency detection method for stereoscopic images grounded on adaptive viewpoint feature enhancement via binocular vision. More specifically, the correlation among left and right views is investigated through a delicately designed binocular stereoscopic saliency feature aggregation module, enabling the generation of more representative saliency features towards binocular vision. Subsequently, to further aggregate the saliency features in multiple scales, we design a progressive attention-based saliency feature pyramid extraction module to effectively integrate the features from top-level to down-level based on the network hierarchy mechanism. The saliency maps are ultimately produced for stereoscopic images by evaluating the obtained saliency features. In addition, we create a stereoscopic image saliency dataset (SIS-3D) that includes 1086 stereoscopic image pairs with various content and their corresponding human eye fixation annotations, aiming to further facilitate the research on visual saliency detection for stereoscopic images. Extensive experiments demonstrate that our proposed method improves CC by an average of 4.02% compared to representative counterparts on the newly built saliency dataset and another publicly available dataset. [ABSTRACT FROM AUTHOR]

Instance-wise contrastive learning (Instance-CL), which learns to map similar instances closer and different instances farther apart in the embedding space, has achieved considerable progress in self-supervised video representation learning. However, canonical Instance-CL does not handle properly the temporal similarities between different videos, limiting the representation capabilities of learned models. This paper presents a novel two-stage framework that combines Instance-CL and unsupervised clustering to progressively learn desirable temporal representations with high intra-class compactness. Specifically, (a) we first introduce a new consistency-preserving sampling strategy to generate positive/negative pairs. Compared to the traditional sampling methods, our sampling strategy focuses more on motion dynamics, resulting in more temporal-related feature representations. (b) To further explore the temporal similarities between videos so as to encourage intra-class compactness, we set temporal representations extracted from Instance-CL as an initializer, and iteratively use k-means clustering to generate pseudo-labels for training the encoder. We term our method as Improved Instance-CL with Deep Clustering (ICDC) and apply it to two downstream tasks, including action recognition and video retrieval. Extensive experimental results show that ICDC gains considerable improvements compared to the existing self-supervised methods. [ABSTRACT FROM AUTHOR]

It has been recognized that texture patterns with abundant high-frequency components, such as grass and water, produce visual masking effects, and the distortion in textures is hard to be perceived by human eyes than structure regions. However, modern video codecs in a rate-distortion optimized manner usually consume a lot of bits to encode textures, leading to the insufficiency in perceptual coding performance. Nowadays, with the rapid development of deep learning, learning based texture synthesis methods have been proposed to replace the coding process of prediction residuals to reduce the rate cost. In this paper, we present a deep texture synthesizer named edge-based texture synthesis framework (ETSF). At encoder side, the framework detects texture regions by semantic and fidelity classification criteria, and the detected regions are quantized coarsely by the hybrid coding framework. In texture characterization, ETSF extracts low-level edge features representing pixel intensity variation. Feature processing tools are developed to remove the spatiotemporal redundancy of edges. The processed edge information is compressed and transmitted. To effectively recover textures, we design an edge-based texture synthesis generative adversarial network (ETSGAN) at the decoder of ETSF, which can incorporate edge information into convolutional layers and generate realistic textures. Experimental results on a collected texture dataset show that the proposed ETSF can achieve an average of -12.8%, -14.2% and -9.6% MOS BD-rate under lowdelay_B, lowdelay_P and random_access configurations of VVC coding, respectively. [ABSTRACT FROM AUTHOR]

Current multi-core processors implement sophisticated hardware prefetchers, that can be configured by application (PID), to improve the system performance. When running multiple applications, each application can present different prefetch requirements, hence different configurations can be used. Setting the optimal prefetch configuration for each application is a complex task since it does not only depend on the application characteristics but also on the interference at the shared memory resources (e.g., memory bandwidth). In his paper, we propose DeepP, a deep learning approach for the IBM POWER8 that identifies at run-time the best prefetch configuration for each application in a workload. To this end, the neural network predicts the performance of each application under the studied prefetch configurations by using a set of performance events. The prediction accuracy of the network is improved thanks to a dynamic training methodology that allows learning the impact of dynamic changes of the prefetch configuration on performance. At run-time, the devised network infers the best prefetch configuration for each application and adjusts it dynamically. Experimental results show that the proposed approach improves performance, on average, by 5.8%, 6.7%, and 15.8% compared to the default prefetch configuration across different 6-, 8-, and 10-application workloads, respectively. [ABSTRACT FROM AUTHOR]

Age-related macular degeneration (AMD) is the leading cause of visual impairment among elderly in the world. Early detection of AMD is of great importance, as the vision loss caused by this disease is irreversible and permanent. Color fundus photography is the most cost-effective imaging modality to screen for retinal disorders. Cutting edge deep learning based algorithms have been recently developed for automatically detecting AMD from fundus images. However, there are still lack of a comprehensive annotated dataset and standard evaluation benchmarks. To deal with this issue, we set up the Automatic Detection challenge on Age-related Macular degeneration (ADAM), which was held as a satellite event of the ISBI 2020 conference. The ADAM challenge consisted of four tasks which cover the main aspects of detecting and characterizing AMD from fundus images, including detection of AMD, detection and segmentation of optic disc, localization of fovea, and detection and segmentation of lesions. As part of the ADAM challenge, we have released a comprehensive dataset of 1200 fundus images with AMD diagnostic labels, pixel-wise segmentation masks for both optic disc and AMD-related lesions (drusen, exudates, hemorrhages and scars, among others), as well as the coordinates corresponding to the location of the macular fovea. A uniform evaluation framework has been built to make a fair comparison of different models using this dataset. During the ADAM challenge, 610 results were submitted for online evaluation, with 11 teams finally participating in the onsite challenge. This paper introduces the challenge, the dataset and the evaluation methods, as well as summarizes the participating methods and analyzes their results for each task. In particular, we observed that the ensembling strategy and the incorporation of clinical domain knowledge were the key to improve the performance of the deep learning models. [ABSTRACT FROM AUTHOR]

Limited angle reconstruction is a typical ill-posed problem in computed tomography (CT). Given incomplete projection data, images reconstructed by conventional analytical algorithms and iterative methods suffer from severe structural distortions and artifacts. In this paper, we proposed a self-augmented multi-stage deep-learning network (Sam’s Net) for end-to-end reconstruction of limited angle CT. With the merit of the alternating minimization technique, Sam’s Net integrates multi-stage self-constraints into cross-domain optimization to provide additional constraints on the manifold of neural networks. In practice, a sinogram completion network (SCNet) and artifact suppression network (ASNet), together with domain transformation layers constitute the backbone for cross-domain optimization. An online self-augmentation module was designed following the manner defined by alternating minimization, which enables a self-augmented learning procedure and multi-stage inference manner. Besides, a substitution operation was applied as a hard constraint for the solution space based on the data fidelity and a learnable weighting layer was constructed for data consistency refinement. Sam’s Net forms a new framework for ill-posed reconstruction problems. In the training phase, the self-augmented procedure guides the optimization into a tightened solution space with enriched diverse data distribution and enhanced data consistency. In the inference phase, multi-stage prediction can improve performance progressively. Extensive experiments with both simulated and practical projections under 90-degree and 120-degree fan-beam configurations validate that Sam’s Net can significantly improve the reconstruction quality with high stability and robustness. [ABSTRACT FROM AUTHOR]

Cephalometric analysis relies on accurate detection of craniomaxillofacial (CMF) landmarks from cone-beam computed tomography (CBCT) images. However, due to the complexity of CMF bony structures, it is difficult to localize landmarks efficiently and accurately. In this paper, we propose a deep learning framework to tackle this challenge by jointly digitalizing 105 CMF landmarks on CBCT images. By explicitly learning the local geometrical relationships between the landmarks, our approach extends Mask R-CNN for end-to-end prediction of landmark locations. Specifically, we first apply a detection network on a down-sampled 3D image to leverage global contextual information to predict the approximate locations of the landmarks. We subsequently leverage local information provided by higher-resolution image patches to refine the landmark locations. On patients with varying non-syndromic jaw deformities, our method achieves an average detection accuracy of 1.38± 0.95mm, outperforming a related state-of-the-art method. [ABSTRACT FROM AUTHOR]

Bioluminescence tomography (BLT) is a promising pre-clinical imaging technique for a wide variety of biomedical applications, which can non-invasively reveal functional activities inside living animal bodies through the detection of visible or near-infrared light produced by bioluminescent reactions. Recently, reconstruction approaches based on deep learning have shown great potential in optical tomography modalities. However, these reports only generate data with stationary patterns of constant target number, shape, and size. The neural networks trained by these data sets are difficult to reconstruct the patterns outside the data sets. This will tremendously restrict the applications of deep learning in optical tomography reconstruction. To address this problem, a self-training strategy is proposed for BLT reconstruction in this paper. The proposed strategy can fast generate large-scale BLT data sets with random target numbers, shapes, and sizes through an algorithm named random seed growth algorithm and the neural network is automatically self-trained. In addition, the proposed strategy uses the neural network to build a map between photon densities on surface and inside the imaged object rather than an end-to-end neural network that directly infers the distribution of sources from the photon density on surface. The map of photon density is further converted into the distribution of sources through the multiplication with stiffness matrix. Simulation, phantom, and mouse studies are carried out. Results show the availability of the proposed self-training strategy. [ABSTRACT FROM AUTHOR]

With the new feature of multi-energy coupling and the advancement of the energy market, Energy Internet (EI) has higher requirements for the efficiency and applicability of integrated energy response. This paper proposes an indirect multi-energy transaction (IMET) to promote multi-energy collaborative optimization in local energy market (LEM) and improve energy utilization through personalized responses from We-Energies (WEs). Firstly, an indirect customer-to-customer multi-energy transaction is modeled for local multi-energy coupling market which can satisfy privacy, preference and autonomy of users. The efficiency of energy matching can be promoted through the participation of conversion devices. In addition, multi-time scale hybrid trading mechanism is constructed with the consideration of the transmission speed of different energy sources. Meanwhile, energy transaction process is built as a Markov decision process (MDP) with deep reinforcement learning algorithm so that the system modeling error can be successfully avoided. Furthermore, a distributed training structure is utilized to obtain more experience for a wider range of scenarios. The results of numerical simulations demonstrate the performance of the proposed method. [ABSTRACT FROM AUTHOR]

Faults are extreme events that canadversely affect the voltages in islanded microgrids. This paper provides a new data-driven methodology for timely prediction of the post-fault voltage stability in hybrid AC/DC microgrids. The proposed method performs a binary classification with delay constraints by processing sequences of the short-time mean squared deviations using a deep learning system. The deep learning system consists of a bidirectional long short-term memory network whose output is a probabilistic voltage instability indicator. When the value of the indicator is non-zero, persistent voltage disturbances are most likely to occur even after the fault clearance. The proposed method enables the microgrid to carry out remedial or preventive actions, such as event-triggered protection and control of distributed energy resources (DERs), which are advantageous to the resilient operation of the microgrids. Extensive and detailed electromagnetic transient (EMT) simulations of a low-voltage hybrid AC/DC microgrid benchmark are analyzed, and the results confirm the effectiveness of the proposed method for online prediction and fast voltage regulation. [ABSTRACT FROM AUTHOR]

Deep learning (DL) techniques have shown promising performance for designing data-driven power system transient stability assessment (TSA) models. However, due to the deep structure of the DL, the resulting model is always a black-box and hard to explain, which hinders its practical adoption by the industry. This paper proposes an interpretable DL-based TSA model to balance the TSA accuracy and transparency. The proposed method combines the strong nonlinear modelling capability of a deep neural network and the interpretability of a decision tree (DT). Through regularizing DL-based model with the average DT path length in the training process, the proposed interpretable DL-based TSA method can visually explain the TSA decision-making process. Simulation results have shown that the proposed method can deliver highly accurate TSA results and interpretable TSA decision-making rules, which can be used for designing preventive control actions. [ABSTRACT FROM AUTHOR]

Sparsity-constrained optimization problems are common in machine learning, such as sparse coding, low-rank minimization and compressive sensing. However, most of previous studies focused on constructing various hand-crafted sparse regularizers, while little work was devoted to learning adaptive sparse regularizers from given input data for specific tasks. In this paper, we propose a deep sparse regularizer learning model that learns data-driven sparse regularizers adaptively. Via the proximal gradient algorithm, we find that the sparse regularizer learning is equivalent to learning a parameterized activation function. This encourages us to learn sparse regularizers in the deep learning framework. Therefore, we build a neural network composed of multiple blocks, each being differentiable and reusable. All blocks contain learnable piecewise linear activation functions which correspond to the sparse regularizer to be learned. Furthermore, the proposed model is trained with back propagation, and all parameters in this model are learned end-to-end. We apply our framework to multi-view clustering and semi-supervised classification tasks to learn a latent compact representation. Experimental results demonstrate the superiority of the proposed framework over state-of-the-art multi-view learning models. [ABSTRACT FROM AUTHOR]

We focus on a fundamental task of detecting meaningful line structures, a.k.a., semantic line, in natural scenes. Many previous methods regard this problem as a special case of object detection and adjust existing object detectors for semantic line detection. However, these methods neglect the inherent characteristics of lines, leading to sub-optimal performance. Lines enjoy much simpler geometric property than complex objects and thus can be compactly parameterized by a few arguments. To better exploit the property of lines, in this paper, we incorporate the classical Hough transform technique into deeply learned representations and propose a one-shot end-to-end learning framework for line detection. By parameterizing lines with slopes and biases, we perform Hough transform to translate deep representations into the parametric domain, in which we perform line detection. Specifically, we aggregate features along candidate lines on the feature map plane and then assign the aggregated features to corresponding locations in the parametric domain. Consequently, the problem of detecting semantic lines in the spatial domain is transformed into spotting individual points in the parametric domain, making the post-processing steps, i.e., non-maximal suppression, more efficient. Furthermore, our method makes it easy to extract contextual line features that are critical for accurate line detection. In addition to the proposed method, we design an evaluation metric to assess the quality of line detection and construct a large scale dataset for the line detection task. Experimental results on our proposed dataset and another public dataset demonstrate the advantages of our method over previous state-of-the-art alternatives. The dataset and source code is available at https://mmcheng.net/dhtline/. [ABSTRACT FROM AUTHOR]

Deep learning recognition approaches can potentially perform better if we can extract a discriminative representation that controllably separates nuisance factors. In this paper, we propose a novel approach to explicitly enforce the extracted discriminative representation $\boldsymbol{d}$ d , extracted latent variation $\boldsymbol{l}$ l (e,g., background, unlabeled nuisance attributes), and semantic variation label vector $\boldsymbol{s}$ s (e.g., labeled expressions/pose) to be independent and complementary to each other. We can cast this problem as an adversarial game in the latent space of an auto-encoder. Specifically, with the to-be-disentangled $\boldsymbol{s}$ s , we propose to equip an end-to-end conditional adversarial network with the ability to decompose an input sample into ${\boldsymbol{d}}$ d and $\boldsymbol{l}$ l . However, we argue that maximizing the cross-entropy loss of semantic variation prediction from $\boldsymbol{d}$ d is not sufficient to remove the impact of $\boldsymbol{s}$ s from $\boldsymbol{d}$ d , and that the uniform-target and entropy regularization are necessary. A collaborative mutual information regularization framework is further proposed to avoid unstable adversarial training. It is able to minimize the differentiable mutual information between the variables to enforce independence. The proposed discriminative representation inherits the desired tolerance property guided by prior knowledge of the task. Our proposed framework achieves top performance on diverse recognition tasks, including digits classification, large-scale face recognition on LFW and IJB-A datasets, and face recognition tolerant to changes in lighting, makeup, disguise, etc. [ABSTRACT FROM AUTHOR]

Graph matching involves combinatorial optimization based on edge-to-edge affinity matrix, which can be generally formulated as Lawler's quadratic assignment problem (QAP). This paper presents a QAP network directly learning with the affinity matrix (equivalently the association graph) whereby the matching problem is translated into a constrained vertex classification task. The association graph is learned by an embedding network for vertex classification, followed by Sinkhorn normalization and a cross-entropy loss for end-to-end learning. We further improve the embedding model on association graph by introducing Sinkhorn based matching-aware constraint, as well as dummy nodes to deal with unequal sizes of graphs. To our best knowledge, this is one of the first network to directly learn with the general Lawler's QAP. In contrast, recent deep matching methods focus on the learning of node/edge features in two graphs respectively. We also show how to extend our network to hypergraph matching, and matching of multiple graphs. Experimental results on both synthetic graphs and real-world images show its effectiveness. For pure QAP tasks on synthetic data and QAPLIB benchmark, our method can perform competitively and even surpass state-of-the-art graph matching and QAP solvers with notable less time cost. We provide a project homepage at http://thinklab.sjtu.edu.cn/project/NGM/index.html. [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]

In this paper, we reveal that metric learning would suffer from serious inseparable problem if without informative sample mining. Since the inseparable samples are often mixed with hard samples, current informative sample mining strategies used to deal with inseparable problem may bring up some side-effects, such as instability of objective function, etc. To alleviate this problem, we propose a novel distance metric learning algorithm, named adaptive neighborhood metric learning (ANML). In ANML, we design two thresholds to adaptively identify the inseparable similar and dissimilar samples in the training procedure, thus inseparable sample removing and metric parameter learning are implemented in the same procedure. Due to the non-continuity of the proposed ANML, we develop an ingenious function, named log-exp mean function to construct a continuous formulation to surrogate it, which can be efficiently solved by the gradient descent method. Similar to Triplet loss, ANML can be used to learn both the linear and deep embeddings. By analyzing the proposed method, we find it has some interesting properties. For example, when ANML is used to learn the linear embedding, current famous metric learning algorithms such as the large margin nearest neighbor (LMNN) and neighbourhood components analysis (NCA) are the special cases of the proposed ANML by setting the parameters different values. When it is used to learn deep features, the state-of-the-art deep metric learning algorithms such as Triplet loss, Lifted structure loss, and Multi-similarity loss become the special cases of ANML. Furthermore, the log-exp mean function proposed in our method gives a new perspective to review the deep metric learning methods such as Prox-NCA and N-pairs loss. At last, promising experimental results demonstrate the effectiveness of the proposed method. [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]

Stereo matching is one of the most popular techniques to estimate dense depth maps by finding the disparity between matching pixels on two, synchronized and rectified images. Alongside with the development of more accurate algorithms, the research community focused on finding good strategies to estimate the reliability, i.e., the confidence, of estimated disparity maps. This information proves to be a powerful cue to naively find wrong matches as well as to improve the overall effectiveness of a variety of stereo algorithms according to different strategies. In this paper, we review more than ten years of developments in the field of confidence estimation for stereo matching. We extensively discuss and evaluate existing confidence measures and their variants, from hand-crafted ones to the most recent, state-of-the-art learning based methods. We study the different behaviors of each measure when applied to a pool of different stereo algorithms and, for the first time in literature, when paired with a state-of-the-art deep stereo network. Our experiments, carried out on five different standard datasets, provide a comprehensive overview of the field, highlighting in particular both strengths and limitations of learning-based strategies. [ABSTRACT FROM AUTHOR]

Stereo matching is one of the longest-standing problems in computer vision with close to 40 years of studies and research. Throughout the years the paradigm has shifted from local, pixel-level decision to various forms of discrete and continuous optimization to data-driven, learning-based methods. Recently, the rise of machine learning and the rapid proliferation of deep learning enhanced stereo matching with new exciting trends and applications unthinkable until a few years ago. Interestingly, the relationship between these two worlds is two-way. While machine, and especially deep, learning advanced the state-of-the-art in stereo matching, stereo itself enabled new ground-breaking methodologies such as self-supervised monocular depth estimation based on deep networks. In this paper, we review recent research in the field of learning-based depth estimation from single and binocular images highlighting the synergies, the successes achieved so far and the open challenges the community is going to face in the immediate future. [ABSTRACT FROM AUTHOR]

Cameras currently allow access to two image states: (i) a minimally processed linear raw-RGB image state (i.e., raw sensor data); or (ii) a highly-processed nonlinear image state (e.g., sRGB). There are many computer vision tasks that work best with a linear image state, such as image deblurring and image dehazing. Unfortunately, the vast majority of images are saved in the nonlinear image state. Because of this, a number of methods have been proposed to “unprocess” nonlinear images back to a raw-RGB state. However, existing unprocessing methods have a drawback because raw-RGB images are sensor-specific. As a result, it is necessary to know which camera produced the sRGB output and use a method or network tailored for that sensor to properly unprocess it. This paper addresses this limitation by exploiting another camera image state that is not available as an output, but it is available inside the camera pipeline. In particular, cameras apply a colorimetric conversion step to convert the raw-RGB image to a device-independent space based on the CIE XYZ color space before they apply the nonlinear photo-finishing. Leveraging this canonical image state, we propose a deep learning framework, CIE XYZ Net, that can unprocess a nonlinear image back to the canonical CIE XYZ image. This image can then be processed by any low-level computer vision operator and re-rendered back to the nonlinear image. We demonstrate the usefulness of the CIE XYZ Net on several low-level vision tasks and show significant gains that can be obtained by this processing framework. Code and dataset are publicly available at https://github.com/mahmoudnafifi/CIE_XYZ_NET. [ABSTRACT FROM AUTHOR]

3D human pose and shape estimation from monocular images has been an active research area in computer vision. Existing deep learning methods for this task rely on high-resolution input, which however, is not always available in many scenarios such as video surveillance and sports broadcasting. Two common approaches to deal with low-resolution images are applying super-resolution techniques to the input, which may result in unpleasant artifacts, or simply training one model for each resolution, which is impractical in many realistic applications. To address the above issues, this paper proposes a novel algorithm called RSC-Net, which consists of a Resolution-aware network, a Self-supervision loss, and a Contrastive learning scheme. The proposed method is able to learn 3D body pose and shape across different resolutions with one single model. The self-supervision loss enforces scale-consistency of the output, and the contrastive learning scheme enforces scale-consistency of the deep features. We show that both these new losses provide robustness when learning in a weakly-supervised manner. Moreover, we extend the RSC-Net to handle low-resolution videos and apply it to reconstruct textured 3D pedestrians from low-resolution input. Extensive experiments demonstrate that the RSC-Net can achieve consistently better results than the state-of-the-art methods for challenging low-resolution images. [ABSTRACT FROM AUTHOR]

Most studies about deep learning are based on neural network models, where many layers of parameterized nonlinear differentiable modules are trained by backpropagation. Recently, it has been shown that deep learning can also be realized by non-differentiable modules without backpropagation training called deep forest. We identify that deep forest has high time costs and memory requirements—this has inhibited its use on large-scale datasets. In this paper, we propose a simple and effective approach with three main strategies for efficient learning of deep forest. First, it substantially reduces the number of instances that needs to be processed through redirecting instances having high predictive confidence straight to the final level for prediction, by-passing all the intermediate levels. Second, many non-informative features are screened out, and only the informative ones are used for learning at each level. Third, an unsupervised feature transformation procedure is proposed to replace the supervised multi-grained scanning procedure. Our theoretical analysis supports the proposed approach in varying the model complexity from low to high as the number of levels increases in deep forest. Experiments show that our approach achieves highly competitive predictive performance with reduced time cost and memory requirement by one to two orders of magnitude. [ABSTRACT FROM AUTHOR]

This paper tackles the joint user association (UA) and power control (PC) problem for dynamic heterogeneous networks (HetNets), where the number of active users varies over time. Since the joint UA and PC problem is a mixed-integer problem, it is challenging to develop a joint UA and PC algorithm that closely achieves the optimal proportional fairness (PF) performance while satisfying the tight computation time budget of recent 3GPP standards. Although previous studies have reduced the computation time on the UA and PC by employing a fully-connected-neural network (FCN), the FCN architecture is not generally applicable to dynamic HetNets because of a varying number of users. In pursuit of scalable neural network design, we propose an unsupervised learning-based UA and PC algorithm using a recurrent neural network (RNN). Notably, in the RNN-based UA, we relax the combinatorial UA variable into a low-dimensional continuous variable, the length of which is invariant to the number of users. The optimality loss in the variable relaxation is upper-bounded by the negligibly small duality gap. Through extensive experiments, we show that the proposed scheme has a 10% higher PF performance than conventional optimization-based methods with the same number of flops and closely achieves the optimal PF performance for various numbers of users. [ABSTRACT FROM AUTHOR]