Ce Zhu

Andrey Ignatov, Radu Timofte, Maurizio Denna et al.

Image super-resolution is a common task on mobile and IoT devices, where one often needs to upscale and enhance low-resolution images and video frames. While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints. In this Mobile AI challenge, we address this problem and propose the participants to design an efficient quantized image super-resolution solution that can demonstrate a real-time performance on mobile NPUs. The participants were provided with the DIV2K dataset and trained INT8 models to do a high-quality 3X image upscaling. The runtime of all models was evaluated on the Synaptics VS680 Smart Home board with a dedicated edge NPU capable of accelerating quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 60 FPS rate when reconstructing Full HD resolution images. A detailed description of all models developed in the challenge is provided in this paper.

Ao Li, Le Zhang, Yun Liu et al.

Transformer-based methods have exhibited remarkable potential in single image super-resolution (SISR) by effectively extracting long-range dependencies. However, most of the current research in this area has prioritized the design of transformer blocks to capture global information, while overlooking the importance of incorporating high-frequency priors, which we believe could be beneficial. In our study, we conducted a series of experiments and found that transformer structures are more adept at capturing low-frequency information, but have limited capacity in constructing high-frequency representations when compared to their convolutional counterparts. Our proposed solution, the cross-refinement adaptive feature modulation transformer (CRAFT), integrates the strengths of both convolutional and transformer structures. It comprises three key components: the high-frequency enhancement residual block (HFERB) for extracting high-frequency information, the shift rectangle window attention block (SRWAB) for capturing global information, and the hybrid fusion block (HFB) for refining the global representation. To tackle the inherent intricacies of transformer structures, we introduce a frequency-guided post-training quantization (PTQ) method aimed at enhancing CRAFT's efficiency. These strategies incorporate adaptive dual clipping and boundary refinement. To further amplify the versatility of our proposed approach, we extend our PTQ strategy to function as a general quantization method for transformer-based SISR techniques. Our experimental findings showcase CRAFT's superiority over current state-of-the-art methods, both in full-precision and quantization scenarios. These results underscore the efficacy and universality of our PTQ strategy. The source code is available at: https://github.com/AVC2-UESTC/Frequency-Inspired-Optimization-for-EfficientSR.git.

Fanxing Liu, Cheng Zeng, Le Zhang et al.

Time series anomaly detection strives to uncover potential abnormal behaviors and patterns from temporal data, and has fundamental significance in diverse application scenarios. Constructing an effective detection model usually requires adequate training data stored in a centralized manner, however, this requirement sometimes could not be satisfied in realistic scenarios. As a prevailing approach to address the above problem, federated learning has demonstrated its power to cooperate with the distributed data available while protecting the privacy of data providers. However, it is still unclear that how existing time series anomaly detection algorithms perform with decentralized data storage and privacy protection through federated learning. To study this, we conduct a federated time series anomaly detection benchmark, named FedTADBench, which involves five representative time series anomaly detection algorithms and four popular federated learning methods. We would like to answer the following questions: (1)How is the performance of time series anomaly detection algorithms when meeting federated learning? (2) Which federated learning method is the most appropriate one for time series anomaly detection? (3) How do federated time series anomaly detection approaches perform on different partitions of data in clients? Numbers of results as well as corresponding analysis are provided from extensive experiments with various settings. The source code of our benchmark is publicly available at https://github.com/fanxingliu2020/FedTADBench.

Jiani Liu, Ce Zhu, Zhen Long et al.

Regression analysis is a key area of interest in the field of data analysis and machine learning which is devoted to exploring the dependencies between variables, often using vectors. The emergence of high dimensional data in technologies such as neuroimaging, computer vision, climatology and social networks, has brought challenges to traditional data representation methods. Tensors, as high dimensional extensions of vectors, are considered as natural representations of high dimensional data. In this book, the authors provide a systematic study and analysis of tensor-based regression models and their applications in recent years. It groups and illustrates the existing tensor-based regression methods and covers the basics, core ideas, and theoretical characteristics of most tensor-based regression methods. In addition, readers can learn how to use existing tensor-based regression methods to solve specific regression tasks with multiway data, what datasets can be selected, and what software packages are available to start related work as soon as possible. Tensor Regression is the first thorough overview of the fundamentals, motivations, popular algorithms, strategies for efficient implementation, related applications, available datasets, and software resources for tensor-based regression analysis. It is essential reading for all students, researchers and practitioners of working on high dimensional data.

Xinwei Ou, Zhangxin Chen, Ce Zhu et al.

Deep neural networks have achieved great success in many data processing applications. However, the high computational complexity and storage cost makes deep learning hard to be used on resource-constrained devices, and it is not environmental-friendly with much power cost. In this paper, we focus on low-rank optimization for efficient deep learning techniques. In the space domain, deep neural networks are compressed by low rank approximation of the network parameters, which directly reduces the storage requirement with a smaller number of network parameters. In the time domain, the network parameters can be trained in a few subspaces, which enables efficient training for fast convergence. The model compression in the spatial domain is summarized into three categories as pre-train, pre-set, and compression-aware methods, respectively. With a series of integrable techniques discussed, such as sparse pruning, quantization, and entropy coding, we can ensemble them in an integration framework with lower computational complexity and storage. Besides of summary of recent technical advances, we have two findings for motivating future works: one is that the effective rank outperforms other sparse measures for network compression. The other is a spatial and temporal balance for tensorized neural networks.

Xinyue Chen, Jie Xu, Yazhou Ren et al.

Federated multi-view clustering has the potential to learn a global clustering model from data distributed across multiple devices. In this setting, label information is unknown and data privacy must be preserved, leading to two major challenges. First, views on different clients often have feature heterogeneity, and mining their complementary cluster information is not trivial. Second, the storage and usage of data from multiple clients in a distributed environment can lead to incompleteness of multi-view data. To address these challenges, we propose a novel federated deep multi-view clustering method that can mine complementary cluster structures from multiple clients, while dealing with data incompleteness and privacy concerns. Specifically, in the server environment, we propose sample alignment and data extension techniques to explore the complementary cluster structures of multiple views. The server then distributes global prototypes and global pseudo-labels to each client as global self-supervised information. In the client environment, multiple clients use the global self-supervised information and deep autoencoders to learn view-specific cluster assignments and embedded features, which are then uploaded to the server for refining the global self-supervised information. Finally, the results of our extensive experiments demonstrate that our proposed method exhibits superior performance in addressing the challenges of incomplete multi-view data in distributed environments.

Jiani Liu, Qinghua Tao, Ce Zhu et al.

Multitask learning (MTL) can utilize the relatedness between multiple tasks for performance improvement. The advent of multimodal data allows tasks to be referenced by multiple indices. High-order tensors are capable of providing efficient representations for such tasks, while preserving structural task-relations. In this paper, a new MTL method is proposed by leveraging low-rank tensor analysis and constructing tensorized Least Squares Support Vector Machines, namely the tLSSVM-MTL, where multilinear modelling and its nonlinear extensions can be flexibly exerted. We employ a high-order tensor for all the weights with each mode relating to an index and factorize it with CP decomposition, assigning a shared factor for all tasks and retaining task-specific latent factors along each index. Then an alternating algorithm is derived for the nonconvex optimization, where each resulting subproblem is solved by a linear system. Experimental results demonstrate promising performances of our tLSSVM-MTL.

Yingcong Lu, Yipeng Liu, Zhen Long et al.

With powerful ability to exploit latent structure of self-representation information, different tensor decompositions have been employed into low rank multi-view clustering (LRMVC) models for achieving significant performance. However, current approaches suffer from a series of problems related to those tensor decomposition, such as the unbalanced matricization scheme, rotation sensitivity, deficient correlations capture and so forth. All these will lead to LRMVC having insufficient access to global information, which is contrary to the target of multi-view clustering. To alleviate these problems, we propose a new tensor decomposition called Tucker-O-Minus Decomposition (TOMD) for multi-view clustering. Specifically, based on the Tucker format, we additionally employ the O-minus structure, which consists of a circle with an efficient bridge linking two weekly correlated factors. In this way, the core tensor in Tucker format is replaced by the O-minus architecture with a more balanced structure, and the enhanced capacity of capturing the global low rank information will be achieved. The proposed TOMD also provides more compact and powerful representation abilities for the self-representation tensor, simultaneously. The alternating direction method of multipliers is used to solve the proposed model TOMD-MVC. Numerical experiments on six benchmark data sets demonstrate the superiority of our proposed method in terms of F-score, precision, recall, normalized mutual information, adjusted rand index, and accuracy.

Le Zhang, Qibin Hou, Yun Liu et al.

Ensemble learning serves as a straightforward way to improve the performance of almost any machine learning algorithm. Existing deep ensemble methods usually naively train many different models and then aggregate their predictions. This is not optimal in our view from two aspects: i) Naively training multiple models adds much more computational burden, especially in the deep learning era; ii) Purely optimizing each base model without considering their interactions limits the diversity of ensemble and performance gains. We tackle these issues by proposing deep negative correlation classification (DNCC), in which the accuracy and diversity trade-off is systematically controlled by decomposing the loss function seamlessly into individual accuracy and the correlation between individual models and the ensemble. DNCC yields a deep classification ensemble where the individual estimator is both accurate and negatively correlated. Thanks to the optimized diversities, DNCC works well even when utilizing a shared network backbone, which significantly improves its efficiency when compared with most existing ensemble systems. Extensive experiments on multiple benchmark datasets and network structures demonstrate the superiority of the proposed method.

Xinyu Lin, Yingjie Zhou, Yipeng Liu et al.

An image line segment is a fundamental low-level visual feature that delineates straight, slender, and uninterrupted portions of objects and scenarios within images. Detection and description of line segments lay the basis for numerous vision tasks. Although many studies have aimed to detect and describe line segments, a comprehensive review is lacking, obstructing their progress. This study fills the gap by comprehensively reviewing related studies on detecting and describing two-dimensional image line segments to provide researchers with an overall picture and deep understanding. Based on their mechanisms, two taxonomies for line segment detection and description are presented to introduce, analyze, and summarize these studies, facilitating researchers to learn about them quickly and extensively. The key issues, core ideas, advantages and disadvantages of existing methods, and their potential applications for each category are analyzed and summarized, including previously unknown findings. The challenges in existing methods and corresponding insights for potentially solving them are also provided to inspire researchers. In addition, some state-of-the-art line segment detection and description algorithms are evaluated without bias, and the evaluation code will be publicly available. The theoretical analysis, coupled with the experimental results, can guide researchers in selecting the best method for their intended vision applications. Finally, this study provides insights for potentially interesting future research directions to attract more attention from researchers to this field.

Zhiwei Lin, Zhe Liu, Yongtao Wang et al.

Perceiving the surrounding environment is a fundamental task in autonomous driving. To obtain highly accurate perception results, modern autonomous driving systems typically employ multi-modal sensors to collect comprehensive environmental data. Among these, the radar-camera multi-modal perception system is especially favored for its excellent sensing capabilities and cost-effectiveness. However, the substantial modality differences between radar and camera sensors pose challenges in fusing information. To address this problem, this paper presents RCBEVDet, a radar-camera fusion 3D object detection framework. Specifically, RCBEVDet is developed from an existing camera-based 3D object detector, supplemented by a specially designed radar feature extractor, RadarBEVNet, and a Cross-Attention Multi-layer Fusion (CAMF) module. Firstly, RadarBEVNet encodes sparse radar points into a dense bird's-eye-view (BEV) feature using a dual-stream radar backbone and a Radar Cross Section aware BEV encoder. Secondly, the CAMF module utilizes a deformable attention mechanism to align radar and camera BEV features and adopts channel and spatial fusion layers to fuse them. To further enhance RCBEVDet's capabilities, we introduce RCBEVDet++, which advances the CAMF through sparse fusion, supports query-based multi-view camera perception models, and adapts to a broader range of perception tasks. Extensive experiments on the nuScenes show that our method integrates seamlessly with existing camera-based 3D perception models and improves their performance across various perception tasks. Furthermore, our method achieves state-of-the-art radar-camera fusion results in 3D object detection, BEV semantic segmentation, and 3D multi-object tracking tasks. Notably, with ViT-L as the image backbone, RCBEVDet++ achieves 72.73 NDS and 67.34 mAP in 3D object detection without test-time augmentation or model ensembling.

Zhiwei Lin, Zhe Liu, Zhongyu Xia et al.

Three-dimensional object detection is one of the key tasks in autonomous driving. To reduce costs in practice, low-cost multi-view cameras for 3D object detection are proposed to replace the expansive LiDAR sensors. However, relying solely on cameras is difficult to achieve highly accurate and robust 3D object detection. An effective solution to this issue is combining multi-view cameras with the economical millimeter-wave radar sensor to achieve more reliable multi-modal 3D object detection. In this paper, we introduce RCBEVDet, a radar-camera fusion 3D object detection method in the bird's eye view (BEV). Specifically, we first design RadarBEVNet for radar BEV feature extraction. RadarBEVNet consists of a dual-stream radar backbone and a Radar Cross-Section (RCS) aware BEV encoder. In the dual-stream radar backbone, a point-based encoder and a transformer-based encoder are proposed to extract radar features, with an injection and extraction module to facilitate communication between the two encoders. The RCS-aware BEV encoder takes RCS as the object size prior to scattering the point feature in BEV. Besides, we present the Cross-Attention Multi-layer Fusion module to automatically align the multi-modal BEV feature from radar and camera with the deformable attention mechanism, and then fuse the feature with channel and spatial fusion layers. Experimental results show that RCBEVDet achieves new state-of-the-art radar-camera fusion results on nuScenes and view-of-delft (VoD) 3D object detection benchmarks. Furthermore, RCBEVDet achieves better 3D detection results than all real-time camera-only and radar-camera 3D object detectors with a faster inference speed at 21~28 FPS. The source code will be released at https://github.com/VDIGPKU/RCBEVDet.

Geyou Zhang, Ce Zhu, Kai Liu et al.

On 3D imaging, light field cameras typically are of single shot, and however, they heavily suffer from low spatial resolution and depth accuracy. In this paper, by employing an optical projector to project a group of single high-frequency phase-shifted sinusoid patterns, we propose a phase guided light field algorithm to significantly improve both the spatial and depth resolutions for off-the-shelf light field cameras. First, for correcting the axial aberrations caused by the main lens of our light field camera, we propose a deformed cone model to calibrate our structured light field system. Second, over wrapped phases computed from patterned images, we propose a stereo matching algorithm, i.e. phase guided sum of absolute difference, to robustly obtain the correspondence for each pair of neighbored two lenslets. Finally, by introducing a virtual camera according to the basic geometrical optics of light field imaging, we propose a reorganization strategy to reconstruct 3D point clouds with spatial-depth high resolution. Experimental results show that, compared with the state-of-the-art active light field methods, the proposed reconstructs 3D point clouds with a spatial resolution of 1280$\times$720 with factors 10$\times$ increased, while maintaining the same high depth resolution and needing merely a single group of high-frequency patterns.

Zifu Zhang, Shengxi Li, Henan Liu et al.

Most recently, learned image compression methods have outpaced traditional hand-crafted standard codecs. However, their inference typically requires to input the whole image at the cost of heavy computing resources, especially for high-resolution image compression; otherwise, the block artefact can exist when compressed by blocks within existing learned image compression methods. To address this issue, we propose a novel continuous patch stitching (CPS) framework for block-wise image compression that is able to achieve seamlessly patch stitching and mathematically eliminate block artefact, thus capable of significantly reducing the required computing resources when compressing images. More specifically, the proposed CPS framework is achieved by padding-free operations throughout, with a newly established parallel overlapping stitching strategy to provide a general upper bound for ensuring the continuity. Upon this, we further propose functional residual blocks with even-sized kernels to achieve down-sampling and up-sampling, together with bottleneck residual blocks retaining feature size to increase network depth. Experimental results demonstrate that our CPS framework achieves the state-of-the-art performance against existing baselines, whilst requiring less than half of computing resources of existing models. Our code shall be released upon acceptance.

Le Zhang, Ao Li, Qibin Hou et al.

Super-resolution (SR) has garnered significant attention within the computer vision community, driven by advances in deep learning (DL) techniques and the growing demand for high-quality visual applications. With the expansion of this field, numerous surveys have emerged. Most existing surveys focus on specific domains, lacking a comprehensive overview of this field. Here, we present an in-depth review of diverse SR methods, encompassing single image super-resolution (SISR), video super-resolution (VSR), stereo super-resolution (SSR), and light field super-resolution (LFSR). We extensively cover over 150 SISR methods, nearly 70 VSR approaches, and approximately 30 techniques for SSR and LFSR. We analyze methodologies, datasets, evaluation protocols, empirical results, and complexity. In addition, we conducted a taxonomy based on each backbone structure according to the diverse purposes. We also explore valuable yet under-studied open issues in the field. We believe that this work will serve as a valuable resource and offer guidance to researchers in this domain. To facilitate access to related work, we created a dedicated repository available at https://github.com/AVC2-UESTC/Holistic-Super-Resolution-Review.

Shengxi Li, Zifu Zhang, Mai Xu et al.

The emerging semantic compression has been receiving increasing research efforts most recently, capable of achieving high fidelity restoration during compression, even at extremely low bitrates. However, existing semantic compression methods typically combine standard pipelines with either pre-defined or high-dimensional semantics, thus suffering from deficiency in compression. To address this issue, we propose a novel hierarchical semantic compression (HSC) framework that purely operates within intrinsic semantic spaces from generative models, which is able to achieve efficient compression for consistent semantic restoration. More specifically, we first analyse the entropy models for the semantic compression, which motivates us to employ a hierarchical architecture based on a newly developed general inversion encoder. Then, we propose the feature compression network (FCN) and semantic compression network (SCN), such that the middle-level semantic feature and core semantics are hierarchically compressed to restore both accuracy and consistency of image semantics, via an entropy model progressively shared by channel-wise context. Experimental results demonstrate that the proposed HSC framework achieves the state-of-the-art performance on subjective quality and consistency for human vision, together with superior performances on machine vision tasks given compressed bitstreams. This essentially coincides with human visual system in understanding images, thus providing a new framework for future image/video compression paradigms. Our code shall be released upon acceptance.

Zhen Long, Qiyuan Wang, Yazhou Ren et al.

Anchor-based large-scale multi-view clustering has attracted considerable attention for its effectiveness in handling massive datasets. However, current methods mainly seek the consensus embedding feature for clustering by exploring global correlations between anchor graphs or projection matrices.In this paper, we propose a simple yet efficient scalable multi-view tensor clustering (S^2MVTC) approach, where our focus is on learning correlations of embedding features within and across views. Specifically, we first construct the embedding feature tensor by stacking the embedding features of different views into a tensor and rotating it. Additionally, we build a novel tensor low-frequency approximation (TLFA) operator, which incorporates graph similarity into embedding feature learning, efficiently achieving smooth representation of embedding features within different views. Furthermore, consensus constraints are applied to embedding features to ensure inter-view semantic consistency. Experimental results on six large-scale multi-view datasets demonstrate that S^2MVTC significantly outperforms state-of-the-art algorithms in terms of clustering performance and CPU execution time, especially when handling massive data. The code of S^2MVTC is publicly available at https://github.com/longzhen520/S2MVTC.

Zhen Long, Ce Zhu, Jie Chen et al.

Tensor-based multi-view subspace clustering (MSC) can capture high-order correlation in the self-representation tensor. Current tensor decompositions for MSC suffer from highly unbalanced unfolding matrices or rotation sensitivity, failing to fully explore inter/intra-view information. Using the advanced tensor network, namely, multi-scale entanglement renormalization ansatz (MERA), we propose a low-rank MERA based MSC (MERA-MSC) algorithm, where MERA factorizes a tensor into contractions of one top core factor and the rest orthogonal/semi-orthogonal factors. Benefiting from multiple interactions among orthogonal/semi-orthogonal (low-rank) factors, the low-rank MERA has a strong representation power to capture the complex inter/intra-view information in the self-representation tensor. The alternating direction method of multipliers is adopted to solve the optimization model. Experimental results on five multi-view datasets demonstrate MERA-MSC has superiority against the compared algorithms on six evaluation metrics. Furthermore, we extend MERA-MSC by incorporating anchor learning to develop a scalable low-rank MERA based multi-view clustering method (sMREA-MVC). The effectiveness and efficiency of sMERA-MVC have been validated on three large-scale multi-view datasets. To our knowledge, this is the first work to introduce MERA to the multi-view clustering topic. The codes of MERA-MSC and sMERA-MVC are publicly available at https://github.com/longzhen520/MERA-MSC.

Shuai Li, Wanqing Li, Chris Cook et al.

Recurrent neural networks (RNNs) have been widely used for processing sequential data. However, RNNs are commonly difficult to train due to the well-known gradient vanishing and exploding problems and hard to learn long-term patterns. Long short-term memory (LSTM) and gated recurrent unit (GRU) were developed to address these problems, but the use of hyperbolic tangent and the sigmoid action functions results in gradient decay over layers. Consequently, construction of an efficiently trainable deep network is challenging. In addition, all the neurons in an RNN layer are entangled together and their behaviour is hard to interpret. To address these problems, a new type of RNN, referred to as independently recurrent neural network (IndRNN), is proposed in this paper, where neurons in the same layer are independent of each other and they are connected across layers. We have shown that an IndRNN can be easily regulated to prevent the gradient exploding and vanishing problems while allowing the network to learn long-term dependencies. Moreover, an IndRNN can work with non-saturated activation functions such as relu (rectified linear unit) and be still trained robustly. Multiple IndRNNs can be stacked to construct a network that is deeper than the existing RNNs. Experimental results have shown that the proposed IndRNN is able to process very long sequences (over 5000 time steps), can be used to construct very deep networks (21 layers used in the experiment) and still be trained robustly. Better performances have been achieved on various tasks by using IndRNNs compared with the traditional RNN and LSTM. The code is available at https://github.com/Sunnydreamrain/IndRNN_Theano_Lasagne.

Lanlan Feng, Ce Zhu, Yipeng Liu et al.

Robust tensor principal component analysis (RTPCA) aims to separate the low-rank and sparse components from multi-dimensional data, making it an essential technique in the signal processing and computer vision fields. Recently emerging tensor singular value decomposition (t-SVD) has gained considerable attention for its ability to better capture the low-rank structure of tensors compared to traditional matrix SVD. However, existing methods often rely on the computationally expensive tensor nuclear norm (TNN), which limits their scalability for real-world tensors. To address this issue, we explore an efficient scaled gradient descent (SGD) approach within the t-SVD framework for the first time, and propose the RTPCA-SGD method. Theoretically, we rigorously establish the recovery guarantees of RTPCA-SGD under mild assumptions, demonstrating that with appropriate parameter selection, it achieves linear convergence to the true low-rank tensor at a constant rate, independent of the condition number. To enhance its practical applicability, we further propose a learnable self-supervised deep unfolding model, which enables effective parameter learning. Numerical experiments on both synthetic and real-world datasets demonstrate the superior performance of the proposed methods while maintaining competitive computational efficiency, especially consuming less time than RTPCA-TNN.

Xinhao Li, Yun Liu, Guolei Sun et al.

Semantic segmentation in videos has been a focal point of recent research. However, existing models encounter challenges when faced with unfamiliar categories. To address this, we introduce the Open Vocabulary Video Semantic Segmentation (OV-VSS) task, designed to accurately segment every pixel across a wide range of open-vocabulary categories, including those that are novel or previously unexplored. To enhance OV-VSS performance, we propose a robust baseline, OV2VSS, which integrates a spatial-temporal fusion module, allowing the model to utilize temporal relationships across consecutive frames. Additionally, we incorporate a random frame enhancement module, broadening the model's understanding of semantic context throughout the entire video sequence. Our approach also includes video text encoding, which strengthens the model's capability to interpret textual information within the video context. Comprehensive evaluations on benchmark datasets such as VSPW and Cityscapes highlight OV-VSS's zero-shot generalization capabilities, especially in handling novel categories. The results validate OV2VSS's effectiveness, demonstrating improved performance in semantic segmentation tasks across diverse video datasets.

Ruituo Wu, Jiani Liu, Ce Zhu et al.

Efficient probability density estimation is a core challenge in statistical machine learning. Tensor-based probabilistic graph methods address interpretability and stability concerns encountered in neural network approaches. However, a substantial number of potential tensor permutations can lead to a tensor network with the same structure but varying expressive capabilities. In this paper, we take tensor ring decomposition for density estimator, which significantly reduces the number of permutation candidates while enhancing expressive capability compared with existing used decompositions. Additionally, a mixture model that incorporates multiple permutation candidates with adaptive weights is further designed, resulting in increased expressive flexibility and comprehensiveness. Different from the prevailing directions of tensor network structure/permutation search, our approach provides a new viewpoint inspired by ensemble learning. This approach acknowledges that suboptimal permutations can offer distinctive information besides that of optimal permutations. Experiments show the superiority of the proposed approach in estimating probability density for moderately dimensional datasets and sampling to capture intricate details.

Yang Chen, Ruituo Wu, Yipeng Liu et al.

Implicit neural representations (INR) suffer from worsening spectral bias, which results in overly smooth solutions to the inverse problem. To deal with this problem, we propose a universal framework for processing inverse problems called \textbf{High-Order Implicit Neural Representations (HOIN)}. By refining the traditional cascade structure to foster high-order interactions among features, HOIN enhances the model's expressive power and mitigates spectral bias through its neural tangent kernel's (NTK) strong diagonal properties, accelerating and optimizing inverse problem resolution. By analyzing the model's expression space, high-order derivatives, and the NTK matrix, we theoretically validate the feasibility of HOIN. HOIN realizes 1 to 3 dB improvements in most inverse problems, establishing a new state-of-the-art recovery quality and training efficiency, thus providing a new general paradigm for INR and paving the way for it to solve the inverse problem.

Geyou Zhang, Ce Zhu, Kai Liu

Phase shifting profilometry (PSP) is favored in high-precision 3D scanning due to its high accuracy, robustness, and pixel-wise property. However, a fundamental assumption of PSP that the object should remain static is violated in dynamic measurement, making PSP susceptible to object moving, resulting in ripple-like errors in the point clouds. We propose a pixel-wise and frame-wise loopable binomial self-compensation (BSC) algorithm to effectively and flexibly eliminate motion error in the four-step PSP. Our mathematical model demonstrates that by summing successive motion-affected phase frames weighted by binomial coefficients, motion error exponentially diminishes as the binomial order increases, accomplishing automatic error compensation through the motion-affected phase sequence, without the assistance of any intermediate variable. Extensive experiments show that our BSC outperforms the existing methods in reducing motion error, while achieving a depth map frame rate equal to the camera's acquisition rate (90 fps), enabling high-accuracy 3D reconstruction with a quasi-single-shot frame rate.

Geyou Zhang, Kai Liu, Ce Zhu

Phase shifting profilometry (PSP) is widely used in high-precision 3D scanning due to its high accuracy, robustness, and pixel-wise handling. However, a fundamental assumption of PSP that the object should remain static does not hold in dynamic measurement, making PSP susceptible to object motion. To address this challenge, our proposed solution, phase-sequential binomial self-compensation (P-BSC), sums successive motion-affected phase frames weighted by binomial coefficients. This approach exponentially reduces the motion error in a pixel-wise and frame-wise loopable manner. Despite its efficacy, P-BSC suffers from high computational overhead and error accumulation due to its reliance on multi-frame phase calculations and weighted summations. Inspired by P-BSC, we propose an image-sequential binomial self-compensation (I-BSC) to weight sum the homogeneous fringe images instead of successive phase frames, which generalizes the BSC concept from phase sequences to image sequences. I-BSC computes the arctangent function only once, resolving both limitations in P-BSC. Extensive analysis, simulations, and experiments show that 1) the proposed BSC outperforms existing methods in reducing motion error while achieving a quasi-single-shot frame rate, i.e., depth map frame rate equals to the camera's acquisition rate, enabling 3D reconstruction with high pixel-depth-temporal resolution; 2) compared to P-BSC, our I-BSC reduces the computational complexity by one polynomial order, thereby accelerating the computational frame rate by several to dozen times, while also reaching faster motion error convergence.

Minghao Han, Weiyi You, Jinhua Zhang et al.

While learned image compression (LIC) focuses on efficient data transmission, generative image compression (GIC) extends this framework by integrating generative modeling to produce photo-realistic reconstructed images. In this paper, we propose a novel diffusion-based generative modeling framework tailored for generative image compression. Unlike prior diffusion-based approaches that indirectly exploit diffusion modeling, we reinterpret the compression process itself as a forward diffusion path governed by stochastic differential equations (SDEs). A reverse neural network is trained to reconstruct images by reversing the compression process directly, without requiring Gaussian noise initialization. This approach achieves smooth rate adjustment and photo-realistic reconstructions with only a minimal number of sampling steps. Extensive experiments on benchmark datasets demonstrate that our method outperforms existing generative image compression approaches across a range of metrics, including perceptual distortion, statistical fidelity, and no-reference quality assessments.

Yang Chen, Ce Zhu, Jiani Liu et al.

Additive models can be used for interpretable machine learning for their clarity and simplicity. However, In the classical models for high-order data, the vectorization operation disrupts the data structure, which may lead to degenerated accuracy and increased computational complexity. To deal with these problems, we propose the tensor polynomial addition model (TPAM). It retains the multidimensional structure information of high-order inputs with tensor representation. The model parameter compression is achieved using a hierarchical and low-order symmetric tensor approximation. In this way, complex high-order feature interactions can be captured with fewer parameters. Moreover, The TPAM preserves the inherent interpretability of additive models, facilitating transparent decision-making and the extraction of meaningful feature values. Additionally, leveraging TPAM's transparency and ability to handle higher-order features, it is used as a post-processing module for other interpretation models by introducing two variants for class activation maps. Experimental results on a series of datasets demonstrate that TPAM can enhance accuracy by up to 30\%, and compression rate by up to 5 times, while maintaining a good interpretability.

Ruituo Wu, Yang Chen, Jian Xiao et al.

Cooperation between temporal convolutional networks (TCN) and graph convolutional networks (GCN) as a processing module has shown promising results in skeleton-based video anomaly detection (SVAD). However, to maintain a lightweight model with low computational and storage complexity, shallow GCN and TCN blocks are constrained by small receptive fields and a lack of cross-dimension interaction capture. To tackle this limitation, we propose a lightweight module called the Dual Attention Module (DAM) for capturing cross-dimension interaction relationships in spatio-temporal skeletal data. It employs the frame attention mechanism to identify the most significant frames and the skeleton attention mechanism to capture broader relationships across fixed partitions with minimal parameters and flops. Furthermore, the proposed Dual Attention Normalizing Flow (DA-Flow) integrates the DAM as a post-processing unit after GCN within the normalizing flow framework. Simulations show that the proposed model is robust against noise and negative samples. Experimental results show that DA-Flow reaches competitive or better performance than the existing state-of-the-art (SOTA) methods in terms of the micro AUC metric with the fewest number of parameters. Moreover, we found that even without training, simply using random projection without dimensionality reduction on skeleton data enables substantial anomaly detection capabilities.

Yuan Fang, Yipeng Liu, Jie Chen et al.

In recent years, the fusion of high spatial resolution multispectral image (HR-MSI) and low spatial resolution hyperspectral image (LR-HSI) has been recognized as an effective method for HSI super-resolution (HSI-SR). However, both HSI and MSI may be acquired under extreme conditions such as night or poorly illuminating scenarios, which may cause different exposure levels, thereby seriously downgrading the yielded HSISR. In contrast to most existing methods based on respective low-light enhancements (LLIE) of MSI and HSI followed by their fusion, a deep Unfolding HSI Super-Resolution with Automatic Exposure Correction (UHSR-AEC) is proposed, that can effectively generate a high-quality fused HSI-SR (in texture and features) even under very imbalanced exposures, thanks to the correlation between LLIE and HSI-SR taken into account. Extensive experiments are provided to demonstrate the state-of-the-art overall performance of the proposed UHSR-AEC, including comparison with some benchmark peer methods.

Xinyu Lin, Yingjie Zhou, Xun Zhang et al.

Binary feature descriptors have been widely used in various visual measurement tasks, particularly those with limited computing resources and storage capacities. Existing binary descriptors may not perform well for long-term visual measurement tasks due to their sensitivity to illumination variations. It can be observed that when image illumination changes dramatically, the relative relationship among local patches mostly remains intact. Based on the observation, consequently, this study presents an illumination-insensitive binary (IIB) descriptor by leveraging the local inter-patch invariance exhibited in multiple spatial granularities to deal with unfavorable illumination variations. By taking advantage of integral images for local patch feature computation, a highly efficient IIB descriptor is achieved. It can encode scalable features in multiple spatial granularities, thus facilitating a computationally efficient hierarchical matching from coarse to fine. Moreover, the IIB descriptor can also apply to other types of image data, such as depth maps and semantic segmentation results, when available in some applications. Numerical experiments on both natural and synthetic datasets reveal that the proposed IIB descriptor outperforms state-of-the-art binary descriptors and some testing float descriptors. The proposed IIB descriptor has also been successfully employed in a demo system for long-term visual localization. The code of the IIB descriptor will be publicly available.

Xinyu Lin, Yingjie Zhou, Yipeng Liu et al.

Line segment detection plays a cornerstone role in computer vision tasks. Among numerous detection methods that have been recently proposed, the ones based on edge drawing attract increasing attention owing to their excellent detection efficiency. However, the existing methods are not robust enough due to the inadequate usage of image gradients for edge drawing and line segment fitting. Based on the observation that the line segments should locate on the edge points with both consistent coordinates and level-line information, i.e., the unit vector perpendicular to the gradient orientation, this paper proposes a level-line guided edge drawing for robust line segment detection (GEDRLSD). The level-line information provides potential directions for edge tracking, which could be served as a guideline for accurate edge drawing. Additionally, the level-line information is fused in line segment fitting to improve the robustness. Numerical experiments show the superiority of the proposed GEDRLSD algorithm compared with state-of-the-art methods.

Yipeng Liu, Yingcong Lu, Weiting Ou et al.

Multi-view subspace clustering methods have employed learned self-representation tensors from different tensor decompositions to exploit low rank information. However, the data structures embedded with self-representation tensors may vary in different multi-view datasets. Therefore, a pre-defined tensor decomposition may not fully exploit low rank information for a certain dataset, resulting in sub-optimal multi-view clustering performance. To alleviate the aforementioned limitations, we propose the adaptively topological tensor network (ATTN) by determining the edge ranks from the structural information of the self-representation tensor, and it can give a better tensor representation with the data-driven strategy. Specifically, in multi-view tensor clustering, we analyze the higher-order correlations among different modes of a self-representation tensor, and prune the links of the weakly correlated ones from a fully connected tensor network. Therefore, the newly obtained tensor networks can efficiently explore the essential clustering information with self-representation with different tensor structures for various datasets. A greedy adaptive rank-increasing strategy is further applied to improve the capture capacity of low rank structure. We apply ATTN on multi-view subspace clustering and utilize the alternating direction method of multipliers to solve it. Experimental results show that multi-view subspace clustering based on ATTN outperforms the counterparts on six multi-view datasets.

Hengling Zhao, Yipeng Liu, Xiaolin Huang et al.

The existing tensor networks adopt conventional matrix product for connection. The classical matrix product requires strict dimensionality consistency between factors, which can result in redundancy in data representation. In this paper, the semi-tensor product is used to generalize classical matrix product-based mode product to semi-tensor mode product. As it permits the connection of two factors with different dimensionality, more flexible and compact tensor decompositions can be obtained with smaller sizes of factors. Tucker decomposition, Tensor Train (TT) and Tensor Ring (TR) are common decomposition for low rank compression of deep neural networks. The semi-tensor product is applied to these tensor decompositions to obtained their generalized versions, i.e., semi-tensor Tucker decomposition (STTu), semi-tensor train(STT) and semi-tensor ring (STR). Experimental results show the STTu, STT and STR achieve higher compression factors than the conventional tensor decompositions with the same accuracy but less training times in ResNet and WideResNetcompression. With 2% accuracy degradation, the TT-RN (rank = 14) and the TR-WRN (rank = 16) only obtain 3 times and99t times compression factors while the STT-RN (rank = 14) and the STR-WRN (rank = 16) achieve 9 times and 179 times compression factors, respectively.

Yingjie Zhou, Xucheng Song, Yanru Zhang et al.

Weakly-supervised anomaly detection aims at learning an anomaly detector from a limited amount of labeled data and abundant unlabeled data. Recent works build deep neural networks for anomaly detection by discriminatively mapping the normal samples and abnormal samples to different regions in the feature space or fitting different distributions. However, due to the limited number of annotated anomaly samples, directly training networks with the discriminative loss may not be sufficient. To overcome this issue, this paper proposes a novel strategy to transform the input data into a more meaningful representation that could be used for anomaly detection. Specifically, we leverage an autoencoder to encode the input data and utilize three factors, hidden representation, reconstruction residual vector, and reconstruction error, as the new representation for the input data. This representation amounts to encode a test sample with its projection on the training data manifold, its direction to its projection and its distance to its projection. In addition to this encoding, we also propose a novel network architecture to seamlessly incorporate those three factors. From our extensive experiments, the benefits of the proposed strategy are clearly demonstrated by its superior performance over the competitive methods.

Jing Wu, Mingyi Zhou, Ce Zhu et al.

Recently, adversarial attack methods have been developed to challenge the robustness of machine learning models. However, mainstream evaluation criteria experience limitations, even yielding discrepancies among results under different settings. By examining various attack algorithms, including gradient-based and query-based attacks, we notice the lack of a consensus on a uniform standard for unbiased performance evaluation. Accordingly, we propose a Piece-wise Sampling Curving (PSC) toolkit to effectively address the aforementioned discrepancy, by generating a comprehensive comparison among adversaries in a given range. In addition, the PSC toolkit offers options for balancing the computational cost and evaluation effectiveness. Experimental results demonstrate our PSC toolkit presents comprehensive comparisons of attack algorithms, significantly reducing discrepancies in practice.

Honggang Chen, Xiaohai He, Linbo Qing et al.

Single image super-resolution (SISR), which aims to reconstruct a high-resolution (HR) image from a low-resolution (LR) observation, has been an active research topic in the area of image processing in recent decades. Particularly, deep learning-based super-resolution (SR) approaches have drawn much attention and have greatly improved the reconstruction performance on synthetic data. Recent studies show that simulation results on synthetic data usually overestimate the capacity to super-resolve real-world images. In this context, more and more researchers devote themselves to develop SR approaches for realistic images. This article aims to make a comprehensive review on real-world single image super-resolution (RSISR). More specifically, this review covers the critical publically available datasets and assessment metrics for RSISR, and four major categories of RSISR methods, namely the degradation modeling-based RSISR, image pairs-based RSISR, domain translation-based RSISR, and self-learning-based RSISR. Comparisons are also made among representative RSISR methods on benchmark datasets, in terms of both reconstruction quality and computational efficiency. Besides, we discuss challenges and promising research topics on RSISR.

Zhonghao Zhang, Yipeng Liu, Xingyu Cao et al.

Deep learning has been used to image compressive sensing (CS) for enhanced reconstruction performance. However, most existing deep learning methods train different models for different subsampling ratios, which brings additional hardware burden. In this paper, we develop a general framework named scalable deep compressive sensing (SDCS) for the scalable sampling and reconstruction (SSR) of all existing end-to-end-trained models. In the proposed way, images are measured and initialized linearly. Two sampling masks are introduced to flexibly control the subsampling ratios used in sampling and reconstruction, respectively. To make the reconstruction model adapt to any subsampling ratio, a training strategy dubbed scalable training is developed. In scalable training, the model is trained with the sampling matrix and the initialization matrix at various subsampling ratios by integrating different sampling matrix masks. Experimental results show that models with SDCS can achieve SSR without changing their structure while maintaining good performance, and SDCS outperforms other SSR methods.

Feng Li, Runmin Cong, Huihui Bai et al.

Recently, convolutional neural network (CNN) has demonstrated significant success for image restoration (IR) tasks (e.g., image super-resolution, image deblurring, rain streak removal, and dehazing). However, existing CNN based models are commonly implemented as a single-path stream to enrich feature representations from low-quality (LQ) input space for final predictions, which fail to fully incorporate preceding low-level contexts into later high-level features within networks, thereby producing inferior results. In this paper, we present a deep interleaved network (DIN) that learns how information at different states should be combined for high-quality (HQ) images reconstruction. The proposed DIN follows a multi-path and multi-branch pattern allowing multiple interconnected branches to interleave and fuse at different states. In this way, the shallow information can guide deep representative features prediction to enhance the feature expression ability. Furthermore, we propose asymmetric co-attention (AsyCA) which is attached at each interleaved node to model the feature dependencies. Such AsyCA can not only adaptively emphasize the informative features from different states, but also improves the discriminative ability of networks. Our presented DIN can be trained end-to-end and applied to various IR tasks. Comprehensive evaluations on public benchmarks and real-world datasets demonstrate that the proposed DIN perform favorably against the state-of-the-art methods quantitatively and qualitatively.

Jing Wu, Mingyi Zhou, Shuaicheng Liu et al.

A single perturbation can pose the most natural images to be misclassified by classifiers. In black-box setting, current universal adversarial attack methods utilize substitute models to generate the perturbation, then apply the perturbation to the attacked model. However, this transfer often produces inferior results. In this study, we directly work in the black-box setting to generate the universal adversarial perturbation. Besides, we aim to design an adversary generating a single perturbation having texture like stripes based on orthogonal matrix, as the top convolutional layers are sensitive to stripes. To this end, we propose an efficient Decision-based Universal Attack (DUAttack). With few data, the proposed adversary computes the perturbation based solely on the final inferred labels, but good transferability has been realized not only across models but also span different vision tasks. The effectiveness of DUAttack is validated through comparisons with other state-of-the-art attacks. The efficiency of DUAttack is also demonstrated on real world settings including the Microsoft Azure. In addition, several representative defense methods are struggling with DUAttack, indicating the practicability of the proposed method.

Keren Fu, Deng-Ping Fan, Ge-Peng Ji et al.

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 ~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.

Jie Xu, Yazhou Ren, Guofeng Li et al.

Multi-view clustering has attracted increasing attentions recently by utilizing information from multiple views. However, existing multi-view clustering methods are either with high computation and space complexities, or lack of representation capability. To address these issues, we propose deep embedded multi-view clustering with collaborative training (DEMVC) in this paper. Firstly, the embedded representations of multiple views are learned individually by deep autoencoders. Then, both consensus and complementary of multiple views are taken into account and a novel collaborative training scheme is proposed. Concretely, the feature representations and cluster assignments of all views are learned collaboratively. A new consistency strategy for cluster centers initialization is further developed to improve the multi-view clustering performance with collaborative training. Experimental results on several popular multi-view datasets show that DEMVC achieves significant improvements over state-of-the-art methods.

Zhen Long, Yipeng Liu, Sixing Zeng et al.

Hyperspectral image (HSI) has some advantages over natural image for various applications due to the extra spectral information. During the acquisition, it is often contaminated by severe noises including Gaussian noise, impulse noise, deadlines, and stripes. The image quality degeneration would badly effect some applications. In this paper, we present a HSI restoration method named smooth and robust low rank tensor recovery. Specifically, we propose a structural tensor decomposition in accordance with the linear spectral mixture model of HSI. It decomposes a tensor into sums of outer matrix vector products, where the vectors are orthogonal due to the independence of endmember spectrums. Based on it, the global low rank tensor structure can be well exposited for HSI denoising. In addition, the 3D anisotropic total variation is used for spatial spectral piecewise smoothness of HSI. Meanwhile, the sparse noise including impulse noise, deadlines and stripes, is detected by the l1 norm regularization. The Frobenius norm is used for the heavy Gaussian noise in some real world scenarios. The alternating direction method of multipliers is adopted to solve the proposed optimization model, which simultaneously exploits the global low rank property and the spatial spectral smoothness of the HSI. Numerical experiments on both simulated and real data illustrate the superiority of the proposed method in comparison with the existing ones.

Yan Min, Mao Ye, Liang Tian et al.

Feature selection is a widely used dimension reduction technique to select feature subsets because of its interpretability. Many methods have been proposed and achieved good results, in which the relationships between adjacent data points are mainly concerned. But the possible associations between data pairs that are may not adjacent are always neglected. Different from previous methods, we propose a novel and very simple approach for unsupervised feature selection, named MMFS (Multi-step Markov transition probability for Feature Selection). The idea is using multi-step Markov transition probability to describe the relation between any data pair. Two ways from the positive and negative viewpoints are employed respectively to keep the data structure after feature selection. From the positive viewpoint, the maximum transition probability that can be reached in a certain number of steps is used to describe the relation between two points. Then, the features which can keep the compact data structure are selected. From the viewpoint of negative, the minimum transition probability that can be reached in a certain number of steps is used to describe the relation between two points. On the contrary, the features that least maintain the loose data structure are selected. And the two ways can also be combined. Thus three algorithms are proposed. Our main contributions are a novel feature section approach which uses multi-step transition probability to characterize the data structure, and three algorithms proposed from the positive and negative aspects for keeping data structure. The performance of our approach is compared with the state-of-the-art methods on eight real-world data sets, and the experimental results show that the proposed MMFS is effective in unsupervised feature selection.

Lihua Zhou, Mao Ye, Xinpeng Li et al.

Recent works in domain adaptation always learn domain invariant features to mitigate the gap between the source and target domains by adversarial methods. The category information are not sufficiently used which causes the learned domain invariant features are not enough discriminative. We propose a new domain adaptation method based on prototype construction which likes capturing data cluster centers. Specifically, it consists of two parts: disentanglement and reconstruction. First, the domain specific features and domain invariant features are disentangled from the original features. At the same time, the domain prototypes and class prototypes of both domains are estimated. Then, a reconstructor is trained by reconstructing the original features from the disentangled domain invariant features and domain specific features. By this reconstructor, we can construct prototypes for the original features using class prototypes and domain prototypes correspondingly. In the end, the feature extraction network is forced to extract features close to these prototypes. Our contribution lies in the technical use of the reconstructor to obtain the original feature prototypes which helps to learn compact and discriminant features. As far as we know, this idea is proposed for the first time. Experiment results on several public datasets confirm the state-of-the-art performance of our method.

Chenpeng Zhang, Shuai Li, Mao Ye et al.

Recurrent neural networks (RNNs) are widely used as a memory model for sequence-related problems. Many variants of RNN have been proposed to solve the gradient problems of training RNNs and process long sequences. Although some classical models have been proposed, capturing long-term dependence while responding to short-term changes remains a challenge. To this problem, we propose a new model named Dual Recurrent Neural Networks (DuRNN). The DuRNN consists of two parts to learn the short-term dependence and progressively learn the long-term dependence. The first part is a recurrent neural network with constrained full recurrent connections to deal with short-term dependence in sequence and generate short-term memory. Another part is a recurrent neural network with independent recurrent connections which helps to learn long-term dependence and generate long-term memory. A selection mechanism is added between two parts to help the needed long-term information transfer to the independent neurons. Multiple modules can be stacked to form a multi-layer model for better performance. Our contributions are: 1) a new recurrent model developed based on the divide-and-conquer strategy to learn long and short-term dependence separately, and 2) a selection mechanism to enhance the separating and learning of different temporal scales of dependence. Both theoretical analysis and extensive experiments are conducted to validate the performance of our model, and we also conduct simple visualization experiments and ablation analyses for the model interpretability. Experimental results indicate that the proposed DuRNN model can handle not only very long sequences (over 5000 time steps), but also short sequences very well. Compared with many state-of-the-art RNN models, our model has demonstrated efficient and better performance.

Zhiyuan Zha, Xin Yuan, Joey Tianyi Zhou et al.

Recent works that utilized deep models have achieved superior results in various image restoration applications. Such approach is typically supervised which requires a corpus of training images with distribution similar to the images to be recovered. On the other hand, the shallow methods which are usually unsupervised remain promising performance in many inverse problems, \eg, image compressive sensing (CS), as they can effectively leverage non-local self-similarity priors of natural images. However, most of such methods are patch-based leading to the restored images with various ringing artifacts due to naive patch aggregation. Using either approach alone usually limits performance and generalizability in image restoration tasks. In this paper, we propose a joint low-rank and deep (LRD) image model, which contains a pair of triply complementary priors, namely \textit{external} and \textit{internal}, \textit{deep} and \textit{shallow}, and \textit{local} and \textit{non-local} priors. We then propose a novel hybrid plug-and-play (H-PnP) framework based on the LRD model for image CS. To make the optimization tractable, a simple yet effective algorithm is proposed to solve the proposed H-PnP based image CS problem. Extensive experimental results demonstrate that the proposed H-PnP algorithm significantly outperforms the state-of-the-art techniques for image CS recovery such as SCSNet and WNNM.

Jing Wu, Xiang Zhang, Mingyi Zhou et al.

Candidate object proposals generated by object detectors based on convolutional neural network (CNN) encounter easy-hard samples imbalance problem, which can affect overall performance. In this study, we propose a Proposal-balanced Network (ProbaNet) for alleviating the imbalance problem. Firstly, ProbaNet increases the probability of choosing hard samples for training by discarding easy samples through threshold truncation. Secondly, ProbaNet emphasizes foreground proposals by increasing their weights. To evaluate the effectiveness of ProbaNet, we train models based on different benchmarks. Mean Average Precision (mAP) of the model using ProbaNet achieves 1.2$\%$ higher than the baseline on PASCAL VOC 2007. Furthermore, it is compatible with existing two-stage detectors and offers a very small amount of additional computational cost.

Shenghan Wang, Yipeng Liu, Lanlan Feng et al.

Robust tensor principal component analysis (RTPCA) can separate the low-rank component and sparse component from multidimensional data, which has been used successfully in several image applications. Its performance varies with different kinds of tensor decompositions, and the tensor singular value decomposition (t-SVD) is a popularly selected one. The standard t-SVD takes the discrete Fourier transform to exploit the residual in the 3rd mode in the decomposition. When minimizing the tensor nuclear norm related to t-SVD, all the frontal slices in frequency domain are optimized equally. In this paper, we incorporate frequency component analysis into t-SVD to enhance the RTPCA performance. Specially, different frequency bands are unequally weighted with respect to the corresponding physical meanings, and the frequency-weighted tensor nuclear norm can be obtained. Accordingly we rigorously deduce the frequency-weighted tensor singular value threshold operator, and apply it for low rank approximation subproblem in RTPCA. The newly obtained frequency-weighted RTPCA can be solved by alternating direction method of multipliers, and it is the first time that frequency analysis is taken in tensor principal component analysis. Numerical experiments on synthetic 3D data, color image denoising and background modeling verify that the proposed method outperforms the state-of-the-art algorithms both in accuracy and computational complexity.

Mingyi Zhou, Jing Wu, Yipeng Liu et al.

Deep learning models are known to be vulnerable to adversarial examples. A practical adversarial attack should require as little as possible knowledge of attacked models. Current substitute attacks need pre-trained models to generate adversarial examples and their attack success rates heavily rely on the transferability of adversarial examples. Current score-based and decision-based attacks require lots of queries for the attacked models. In this study, we propose a novel adversarial imitation attack. First, it produces a replica of the attacked model by a two-player game like the generative adversarial networks (GANs). The objective of the generative model is to generate examples that lead the imitation model returning different outputs with the attacked model. The objective of the imitation model is to output the same labels with the attacked model under the same inputs. Then, the adversarial examples generated by the imitation model are utilized to fool the attacked model. Compared with the current substitute attacks, imitation attacks can use less training data to produce a replica of the attacked model and improve the transferability of adversarial examples. Experiments demonstrate that our imitation attack requires less training data than the black-box substitute attacks, but achieves an attack success rate close to the white-box attack on unseen data with no query.

Mingyi Zhou, Jing Wu, Yipeng Liu et al.

Machine learning models are vulnerable to adversarial examples. For the black-box setting, current substitute attacks need pre-trained models to generate adversarial examples. However, pre-trained models are hard to obtain in real-world tasks. In this paper, we propose a data-free substitute training method (DaST) to obtain substitute models for adversarial black-box attacks without the requirement of any real data. To achieve this, DaST utilizes specially designed generative adversarial networks (GANs) to train the substitute models. In particular, we design a multi-branch architecture and label-control loss for the generative model to deal with the uneven distribution of synthetic samples. The substitute model is then trained by the synthetic samples generated by the generative model, which are labeled by the attacked model subsequently. The experiments demonstrate the substitute models produced by DaST can achieve competitive performance compared with the baseline models which are trained by the same train set with attacked models. Additionally, to evaluate the practicability of the proposed method on the real-world task, we attack an online machine learning model on the Microsoft Azure platform. The remote model misclassifies 98.35% of the adversarial examples crafted by our method. To the best of our knowledge, we are the first to train a substitute model for adversarial attacks without any real data.