arXiv subjects

Jing Zhang

Publications and source records attributed to Jing Zhang.

At least 631 records · Page 35Linked to original sources

arXiv2023

Audio-Visual Segmentation with Semantics

We propose a new problem called audio-visual segmentation (AVS), in which the goal is to output a pixel-level map of the object(s) that produce sound at the time of the image frame. To facilitate this research, we construct the first audio-visual segmentation benchmark, i.e., AVSBench, providing pixel-wise annotations for sounding objects in audible videos. It contains three subsets: AVSBench-object (Single-source subset, Multi-sources subset) and AVSBench-semantic (Semantic-labels subset). Accordingly, three settings are studied: 1) semi-supervised audio-visual segmentation with a single sound source; 2) fully-supervised audio-visual segmentation with multiple sound sources, and 3) fully-supervised audio-visual semantic segmentation. The first two settings need to generate binary masks of sounding objects indicating pixels corresponding to the audio, while the third setting further requires generating semantic maps indicating the object category. To deal with these problems, we propose a new baseline method that uses a temporal pixel-wise audio-visual interaction module to inject audio semantics as guidance for the visual segmentation process. We also design a regularization loss to encourage audio-visual mapping during training. Quantitative and qualitative experiments on AVSBench compare our approach to several existing methods for related tasks, demonstrating that the proposed method is promising for building a bridge between the audio and pixel-wise visual semantics. Code is available at https://github.com/OpenNLPLab/AVSBench. Online benchmark is available at http://www.avlbench.opennlplab.cn.

cs.CV↗

arXiv2023

Hexapartite steering based on a four-wave-mixing process with a spatially structured pump

Multipartite Einstein-Podolsky-Rosen (EPR) steering has been widely studied, for realizing safer quantum communication. The steering properties of six spatially separated beams from the four-wave-mixing process with a spatially structured pump are investigated. Behaviors of all (1+i)/(i+1)-mode (i=1,2,3) steerings are understandable, if the role of the corresponding relative interaction strengths are taken into account. Moreover, stronger collective multipartite steerings including five modes also can be obtained in our scheme, which has potential applications in ultra-secure multiuser quantum networks when the issue of trust is critical. By further discussing about all monogamy relations, it is noticed that the type-IV monogamy relations, which are naturally included in our model, are conditionally satisfied. Matrix representation is used to express the steerings for the first time, which is very useful to understand the monogomy relations intuitively. Different steering properties obtained in this compact phase-insensitive scheme have potential applications for different kinds of quantum communication tasks.

quant-ph↗

arXiv2023

Towards Deeper Understanding of Camouflaged Object Detection

Preys in the wild evolve to be camouflaged to avoid being recognized by predators. In this way, camouflage acts as a key defence mechanism across species that is critical to survival. To detect and segment the whole scope of a camouflaged object, camouflaged object detection (COD) is introduced as a binary segmentation task, with the binary ground truth camouflage map indicating the exact regions of the camouflaged objects. In this paper, we revisit this task and argue that the binary segmentation setting fails to fully understand the concept of camouflage. We find that explicitly modeling the conspicuousness of camouflaged objects against their particular backgrounds can not only lead to a better understanding about camouflage, but also provide guidance to designing more sophisticated camouflage techniques. Furthermore, we observe that it is some specific parts of camouflaged objects that make them detectable by predators. With the above understanding about camouflaged objects, we present the first triple-task learning framework to simultaneously localize, segment, and rank camouflaged objects, indicating the conspicuousness level of camouflage. As no corresponding datasets exist for either the localization model or the ranking model, we generate localization maps with an eye tracker, which are then processed according to the instance level labels to generate our ranking-based training and testing dataset. We also contribute the largest COD testing set to comprehensively analyse performance of the COD models. Experimental results show that our triple-task learning framework achieves new state-of-the-art, leading to a more explainable COD network. Our code, data, and results are available at: \url{https://github.com/JingZhang617/COD-Rank-Localize-and-Segment}.

cs.CV↗

arXiv2022

Generative Transformer for Accurate and Reliable Salient Object Detection

Transformer, which originates from machine translation, is particularly powerful at modeling long-range dependencies. Currently, the transformer is making revolutionary progress in various vision tasks, leading to significant performance improvements compared with the convolutional neural network (CNN) based frameworks. In this paper, we conduct extensive research on exploiting the contributions of transformers for accurate and reliable salient object detection. For the former, we apply transformer to a deterministic model, and explain that the effective structure modeling and global context modeling abilities lead to its superior performance compared with the CNN based frameworks. For the latter, we observe that both CNN and transformer based frameworks suffer greatly from the over-confidence issue, where the models tend to generate wrong predictions with high confidence. To estimate the reliability degree of both CNN- and transformer-based frameworks, we further present a latent variable model, namely inferential generative adversarial network (iGAN), based on the generative adversarial network (GAN). The stochastic attribute of the latent variable makes it convenient to estimate the predictive uncertainty, serving as an auxiliary output to evaluate the reliability of model prediction. Different from the conventional GAN, which defines the distribution of the latent variable as fixed standard normal distribution $\mathcal{N}(0,\mathbf{I})$, the proposed iGAN infers the latent variable by gradient-based Markov Chain Monte Carlo (MCMC), namely Langevin dynamics, leading to an input-dependent latent variable model. We apply our proposed iGAN to both fully and weakly supervised salient object detection, and explain that iGAN within the transformer framework leads to both accurate and reliable salient object detection.

cs.CV↗

arXiv2022

PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation

The Depth-aware Video Panoptic Segmentation (DVPS) is a new challenging vision problem that aims to predict panoptic segmentation and depth in a video simultaneously. The previous work solves this task by extending the existing panoptic segmentation method with an extra dense depth prediction and instance tracking head. However, the relationship between the depth and panoptic segmentation is not well explored -- simply combining existing methods leads to competition and needs carefully weight balancing. In this paper, we present PolyphonicFormer, a vision transformer to unify these sub-tasks under the DVPS task and lead to more robust results. Our principal insight is that the depth can be harmonized with the panoptic segmentation with our proposed new paradigm of predicting instance level depth maps with object queries. Then the relationship between the two tasks via query-based learning is explored. From the experiments, we demonstrate the benefits of our design from both depth estimation and panoptic segmentation aspects. Since each thing query also encodes the instance-wise information, it is natural to perform tracking directly with appearance learning. Our method achieves state-of-the-art results on two DVPS datasets (Semantic KITTI, Cityscapes), and ranks 1st on the ICCV-2021 BMTT Challenge video + depth track. Code is available at https://github.com/HarborYuan/PolyphonicFormer .

cs.CV↗

arXiv2022

A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learning

With the development of convolutional neural networks, hundreds of deep learning based dehazing methods have been proposed. In this paper, we provide a comprehensive survey on supervised, semi-supervised, and unsupervised single image dehazing. We first discuss the physical model, datasets, network modules, loss functions, and evaluation metrics that are commonly used. Then, the main contributions of various dehazing algorithms are categorized and summarized. Further, quantitative and qualitative experiments of various baseline methods are carried out. Finally, the unsolved issues and challenges that can inspire the future research are pointed out. A collection of useful dehazing materials is available at \url{https://github.com/Xiaofeng-life/AwesomeDehazing}.

cs.CV↗

arXiv2022

Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model

Large-scale vision foundation models have made significant progress in visual tasks on natural images, with vision transformers being the primary choice due to their good scalability and representation ability. However, large-scale models in remote sensing (RS) have not yet been sufficiently explored. In this paper, we resort to plain vision transformers with about 100 million parameters and make the first attempt to propose large vision models tailored to RS tasks and investigate how such large models perform. To handle the large sizes and objects of arbitrary orientations in RS images, we propose a new rotated varied-size window attention to replace the original full attention in transformers, which can significantly reduce the computational cost and memory footprint while learning better object representation by extracting rich context from the generated diverse windows. Experiments on detection tasks show the superiority of our model over all state-of-the-art models, achieving 81.24% mAP on the DOTA-V1.0 dataset. The results of our models on downstream classification and segmentation tasks also show competitive performance compared to existing advanced methods. Further experiments show the advantages of our models in terms of computational complexity and data efficiency in transferring.

cs.CV↗

arXiv2022

Learning to Learn Better for Video Object Segmentation

Recently, the joint learning framework (JOINT) integrates matching based transductive reasoning and online inductive learning to achieve accurate and robust semi-supervised video object segmentation (SVOS). However, using the mask embedding as the label to guide the generation of target features in the two branches may result in inadequate target representation and degrade the performance. Besides, how to reasonably fuse the target features in the two different branches rather than simply adding them together to avoid the adverse effect of one dominant branch has not been investigated. In this paper, we propose a novel framework that emphasizes Learning to Learn Better (LLB) target features for SVOS, termed LLB, where we design the discriminative label generation module (DLGM) and the adaptive fusion module to address these issues. Technically, the DLGM takes the background-filtered frame instead of the target mask as input and adopts a lightweight encoder to generate the target features, which serves as the label of the online few-shot learner and the value of the decoder in the transformer to guide the two branches to learn more discriminative target representation. The adaptive fusion module maintains a learnable gate for each branch, which reweighs the element-wise feature representation and allows an adaptive amount of target information in each branch flowing to the fused target feature, thus preventing one branch from being dominant and making the target feature more robust to distractor. Extensive experiments on public benchmarks show that our proposed LLB method achieves state-of-the-art performance.

cs.CV↗

arXiv2022

On equations $(-1)^αp^x+(-1)^β(2^k(2p+1))^y=z^2$ with Sophie Germain prime $p$

In this paper, we consider the Diophantine equation $(-1)^αp^x+(-1)^β(2^k(2p+1))^y=z^2$ for Sophie Germain prime $p$ with $α, β\in\{0,1\}$, $αβ=0$ and $k\geq 0$. First, for $p=2$, we solve three Diophantine equations $(-1)^α2^x+(-1)^β(2^{k} 5)^y=z^2$ by using Nagell-Lijunggren Equation and the database LMFDB of elliptic curve $y^2=x^3+ax+b$ over $\mathbb{Q}$. Then we obtain all non-negative integer solutions for the following four types of equations for odd Sophie Germain prime $p$: i) $p^x+(2^{2k+1}(2p+1))^y=z^2$ with $p\equiv 3, 5 \pmod 8$ and $k\geq 0$; ii) $p^x+(2^{2k}(2p+1))^y=z^2$ with $p\equiv 3 \pmod 8$ and $k\geq 1$; iii) $p^x-(2^{k}(2p+1))^y=z^2$ with $p\equiv 3 \pmod 4$ and $k\geq 0$; iv) $-p^x+(2^{k}(2p+1))^y=z^2$ with $p\equiv 1, 3, 5 \pmod 8$ and $k\geq 1$; For each type of the equations, we show the existences of such prime $p$. Since it was conjectured that there exist infinitely many Sophie Germain primes in literature, it is reasonable to conjecture that there exist infinite Sophie Germain primes $p$ such that $p\equiv k \pmod 8$ for any $k\in\{1,3,5,7\}$.

math.NT↗

arXiv2022

Federated Learning-Based Cell-Free Massive MIMO System for Privacy-Preserving

Cell-free massive MIMO (CF mMIMO) is a promising next generation wireless architecture to realize federated learning (FL). However, sensitive information of user equipments (UEs) may be exposed to the involved access points or the central processing unit in practice. To guarantee data privacy, effective privacy-preserving mechanisms are defined in this paper. In particular, we demonstrate and characterize the possibility in exploiting the inherent quantization error, caused by low-resolution analog-to-digital converters (ADCs) and digital-to-analog converters (DACs), for privacy-preserving in a FL CF mMIMO system. Furthermore, to reduce the required uplink training time in such a system, a stochastic non-convex design problem that jointly optimizing the transmit power and the data rate is formulated. To address the problem at hand, we propose a novel power control method by utilizing the successive convex approximation approach to obtain a suboptimal solution. Besides, an asynchronous protocol is established for mitigating the straggler effect to facilitate FL. Numerical results show that compared with the conventional full power transmission, adopting the proposed power control method can effectively reduce the uplink training time under various practical system settings. Also, our results unveil that our proposed asynchronous approach can reduce the waiting time at the central processing unit for receiving all user information, as there are no stragglers that requires a long time to report their local updates.

cs.IT↗

arXiv2022

DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer

Recently, Transformer-based methods, which predict polygon points or Bezier curve control points for localizing texts, are popular in scene text detection. However, these methods built upon detection transformer framework might achieve sub-optimal training efficiency and performance due to coarse positional query modeling.In addition, the point label form exploited in previous works implies the reading order of humans, which impedes the detection robustness from our observation. To address these challenges, this paper proposes a concise Dynamic Point Text DEtection TRansformer network, termed DPText-DETR. In detail, DPText-DETR directly leverages explicit point coordinates to generate position queries and dynamically updates them in a progressive way. Moreover, to improve the spatial inductive bias of non-local self-attention in Transformer, we present an Enhanced Factorized Self-Attention module which provides point queries within each instance with circular shape guidance. Furthermore, we design a simple yet effective positional label form to tackle the side effect of the previous form. To further evaluate the impact of different label forms on the detection robustness in real-world scenario, we establish an Inverse-Text test set containing 500 manually labeled images. Extensive experiments prove the high training efficiency, robustness, and state-of-the-art performance of our method on popular benchmarks. The code and the Inverse-Text test set are available at https://github.com/ymy-k/DPText-DETR.

cs.CV↗

arXiv2022

1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results

The 1$^{\text{st}}$ Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and organized several subchallenges in this domain: (i) UAV-based Maritime Object Detection, (ii) UAV-based Maritime Object Tracking, (iii) USV-based Maritime Obstacle Segmentation and (iv) USV-based Maritime Obstacle Detection. The subchallenges were based on the SeaDronesSee and MODS benchmarks. This report summarizes the main findings of the individual subchallenges and introduces a new benchmark, called SeaDronesSee Object Detection v2, which extends the previous benchmark by including more classes and footage. We provide statistical and qualitative analyses, and assess trends in the best-performing methodologies of over 130 submissions. The methods are summarized in the appendix. The datasets, evaluation code and the leaderboard are publicly available at https://seadronessee.cs.uni-tuebingen.de/macvi.

cs.CV↗

arXiv2022

ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond

Vision transformers have shown great potential in various computer vision tasks owing to their strong capability to model long-range dependency using the self-attention mechanism. Nevertheless, they treat an image as a 1D sequence of visual tokens, lacking an intrinsic inductive bias (IB) in modeling local visual structures and dealing with scale variance, which is instead learned implicitly from large-scale training data with longer training schedules. In this paper, we propose a Vision Transformer Advanced by Exploring intrinsic IB from convolutions, i.e., ViTAE. Technically, ViTAE has several spatial pyramid reduction modules to downsample and embed the input image into tokens with rich multi-scale context using multiple convolutions with different dilation rates. In this way, it acquires an intrinsic scale invariance IB and can learn robust feature representation for objects at various scales. Moreover, in each transformer layer, ViTAE has a convolution block parallel to the multi-head self-attention module, whose features are fused and fed into the feed-forward network. Consequently, it has the intrinsic locality IB and is able to learn local features and global dependencies collaboratively. The proposed two kinds of cells are stacked in both isotropic and multi-stage manners to formulate two families of ViTAE models, i.e., the vanilla ViTAE and ViTAEv2. Experiments on the ImageNet dataset as well as downstream tasks on the MS COCO, ADE20K, and AP10K datasets validate the superiority of our models over the baseline transformer models and concurrent works. Besides, we scale up our ViTAE model to 644M parameters and obtain the state-of-the-art classification performance, i.e., 88.5% Top-1 classification accuracy on ImageNet validation set and the best 91.2% Top-1 accuracy on ImageNet real validation set, without using extra private data.

cs.CV↗

arXiv2022

GLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point Clouds

Current 3D single object tracking methods are typically based on VoteNet, a 3D region proposal network. Despite the success, using a single seed point feature as the cue for offset learning in VoteNet prevents high-quality 3D proposals from being generated. Moreover, seed points with different importance are treated equally in the voting process, aggravating this defect. To address these issues, we propose a novel global-local transformer voting scheme to provide more informative cues and guide the model pay more attention on potential seed points, promoting the generation of high-quality 3D proposals. Technically, a global-local transformer (GLT) module is employed to integrate object- and patch-aware prior into seed point features to effectively form strong feature representation for geometric positions of the seed points, thus providing more robust and accurate cues for offset learning. Subsequently, a simple yet effective training strategy is designed to train the GLT module. We develop an importance prediction branch to learn the potential importance of the seed points and treat the output weights vector as a training constraint term. By incorporating the above components together, we exhibit a superior tracking method GLT-T. Extensive experiments on challenging KITTI and NuScenes benchmarks demonstrate that GLT-T achieves state-of-the-art performance in the 3D single object tracking task. Besides, further ablation studies show the advantages of the proposed global-local transformer voting scheme over the original VoteNet. Code and models will be available at https://github.com/haooozi/GLT-T.

cs.CV↗

arXiv2022

Toward Real-world Single Image Deraining: A New Benchmark and Beyond

Single image deraining (SID) in real scenarios attracts increasing attention in recent years. Due to the difficulty in obtaining real-world rainy/clean image pairs, previous real datasets suffer from low-resolution images, homogeneous rain streaks, limited background variation, and even misalignment of image pairs, resulting in incomprehensive evaluation of SID methods. To address these issues, we establish a new high-quality dataset named RealRain-1k, consisting of $1,120$ high-resolution paired clean and rainy images with low- and high-density rain streaks, respectively. Images in RealRain-1k are automatically generated from a large number of real-world rainy video clips through a simple yet effective rain density-controllable filtering method, and have good properties of high image resolution, background diversity, rain streaks variety, and strict spatial alignment. RealRain-1k also provides abundant rain streak layers as a byproduct, enabling us to build a large-scale synthetic dataset named SynRain-13k by pasting the rain streak layers on abundant natural images. Based on them and existing datasets, we benchmark more than 10 representative SID methods on three tracks: (1) fully supervised learning on RealRain-1k, (2) domain generalization to real datasets, and (3) syn-to-real transfer learning. The experimental results (1) show the difference of representative methods in image restoration performance and model complexity, (2) validate the significance of the proposed datasets for model generalization, and (3) provide useful insights on the superiority of learning from diverse domains and shed lights on the future research on real-world SID. The datasets will be released at https://github.com/hiker-lw/RealRain-1k

cs.CV↗

arXiv2022

Generalized weighted number operators on functionals of discrete-time normal martingales

Let $M$ be a discrete-time normal martingale that has the chaotic representation property. Then, from the space of square integrable functionals of $M$, one can construct generalized functionals of $M$. In this paper, by using a type of weights, we introduce a class of continuous linear operators acting on generalized functionals of $M$, which we call generalized weighted number (GWN) operators. We prove that GWN operators can be represented in terms of generalized annihilation and creation operators (acting on generalized functionals of $M$). We also examine commutation relations between a GWN operator and a generalized annihilation (or creation) operator, and obtain several formulas expressing such commutation relations.

math.PR↗

arXiv2022

Energy-Based Residual Latent Transport for Unsupervised Point Cloud Completion

Unsupervised point cloud completion aims to infer the whole geometry of a partial object observation without requiring partial-complete correspondence. Differing from existing deterministic approaches, we advocate generative modeling based unsupervised point cloud completion to explore the missing correspondence. Specifically, we propose a novel framework that performs completion by transforming a partial shape encoding into a complete one using a latent transport module, and it is designed as a latent-space energy-based model (EBM) in an encoder-decoder architecture, aiming to learn a probability distribution conditioned on the partial shape encoding. To train the latent code transport module and the encoder-decoder network jointly, we introduce a residual sampling strategy, where the residual captures the domain gap between partial and complete shape latent spaces. As a generative model-based framework, our method can produce uncertainty maps consistent with human perception, leading to explainable unsupervised point cloud completion. We experimentally show that the proposed method produces high-fidelity completion results, outperforming state-of-the-art models by a significant margin.

cs.CV↗

arXiv2022

SPOC learner's final grade prediction based on a novel sampling batch normalization embedded neural network method

Recent years have witnessed the rapid growth of Small Private Online Courses (SPOC) which is able to highly customized and personalized to adapt variable educational requests, in which machine learning techniques are explored to summarize and predict the learner's performance, mostly focus on the final grade. However, the problem is that the final grade of learners on SPOC is generally seriously imbalance which handicaps the training of prediction model. To solve this problem, a sampling batch normalization embedded deep neural network (SBNEDNN) method is developed in this paper. First, a combined indicator is defined to measure the distribution of the data, then a rule is established to guide the sampling process. Second, the batch normalization (BN) modified layers are embedded into full connected neural network to solve the data imbalanced problem. Experimental results with other three deep learning methods demonstrates the superiority of the proposed method.

cs.CV↗