检索结果-内蒙古大学图书馆

Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Diao, Yunfeng Wang, He Shao, Tianjia Yang, Yongliang Zhou, Kun Hogg, David Wang, Meng School of Computer Science and Information Engineering Hefei University of Technology Hefei China Department of Computer Science University College London London United Kingdom State Key Lab of CAD&CG Zhejiang University Hangzhou China Department of Computer Science University of Bath Bath United Kingdom School of Computing University of Leeds Leeds United Kingdom

Human Activity Recognition (HAR) has been employed in a wide range of applications, e.g. self-driving cars, where safety and lives are at stake. Recently, the robustness of skeleton-based HAR methods have been questioned due to their vulnerability to adversarial attacks. However, the proposed attacks require the full-knowledge of the attacked classifier, which is overly restrictive. In this paper, we show such threats indeed exist, even when the attacker only has access to the input/output of the model. To this end, we propose the very first black-box adversarial attack approach in skeleton-based HAR called BASAR. BASAR explores the interplay between the classification boundary and the natural motion manifold. To our best knowledge, this is the first time data manifold is introduced in adversarial attacks on time series. Via BASAR, we find on-manifold adversarial samples are extremely deceitful and rather common in skeletal motions, in contrast to the common belief that adversarial samples only exist off-manifold. Through exhaustive evaluation, we show that BASAR can deliver successful attacks across classifiers, datasets, and attack modes. By attack, BASAR helps identify the potential causes of the model vulnerability and provides insights on possible improvements. Finally, to mitigate the newly identified threat, we propose a new adversarial training approach by leveraging the sophisticated distributions of on/off-manifold adversarial samples, called mixed manifold-based adversarial training (MMAT). MMAT can successfully help defend against adversarial attacks without compromising classification accuracy. Copyright © 2022, The Authors. All rights reserved.

关键词： Musculoskeletal system

Fast and Robust Non-Rigid Registration Using Accelerated Majorization-Minimization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yao, Yuxin Deng, Bailin Xu, Weiwei Zhang, Juyong School of Mathematical Sciences University of Science and Technology of China China School of Computer Science and Informatics Cardiff University United Kingdom State Key Lab of CAD & CG Department of Computer Science Zhejiang University China

Non-rigid 3D registration, which deforms a source 3D shape in a non-rigid way to align with a target 3D shape, is a classical problem in computer vision. Such problems can be challenging because of imperfect data (noise, outliers and partial overlap) and high degrees of freedom. Existing methods typically adopt the p type robust norm to measure the alignment error and regularize the smoothness of deformation, and use a proximal algorithm to solve the resulting non-smooth optimization problem. However, the slow convergence of such algorithms limits their wide applications. In this paper, we propose a formulation for robust non-rigid registration based on a globally smooth robust norm for alignment and regularization, which can effectively handle outliers and partial overlaps. The problem is solved using the majorization-minimization algorithm, which reduces each iteration to a convex quadratic problem with a closed-form solution. We further apply Anderson acceleration to speed up the convergence of the solver, enabling the solver to run efficiently on devices with limited compute capability. Extensive experiments demonstrate the effectiveness of our method for non-rigid alignment between two shapes with outliers and partial overlaps, with quantitative evaluation showing that it outperforms state-of-the-art methods in terms of registration accuracy and computational speed. The source code is available at https://***/yaoyx689/AMM_NRR. Copyright © 2022, The Authors. All rights reserved.

关键词： Iterative methods

Learning Photometric Feature Transform for Free-form Object Scan

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Feng, Xiang Kang, Kaizhang Pei, Fan Ding, Huakeng You, Jinjiang Tan, Ping Zhou, Kun Wu, Hongzhi The State Key Lab of CAD & CG Zhejiang University Hangzhou310058 China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong The Visual Computing Center King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia

We propose a novel framework to automatically learn to aggregate and transform photometric measurements from multiple unstructured views into spatially distinctive and view-invariant low-level features, which are subsequently fed to a multi-view stereo pipeline to enhance 3D reconstruction. The illumination conditions during acquisition and the feature transform are jointly trained on a large amount of synthetic data. We further build a system to reconstruct both the geometry and anisotropic reflectance of a variety of challenging objects from hand-held scans. The effectiveness of the system is demonstrated with a lightweight prototype, consisting of a camera and an array of LEDs, as well as an off-the-shelf tablet. Our results are validated against reconstructions from a professional 3D scanner and photographs, and compare favorably with state-of-the-art techniques. Copyright © 2023, The Authors. All rights reserved.

关键词： Stereo image processing

Adversarial mutual information for text generation 37

学校读者我要写书评

暂无评论

Adversarial mutual information for text generation

37th International Conference on Machine Learning, ICML 2020

作者： Pan, Boyuan Yang, Yazheng Liang, Kaizhao Kailkhura, Bhavya Jin, Zhongming Hua, Xian-Sheng Cai, Deng Li, Bo State Key Lab of CAD&CG Zhejiang University China College of Computer Science Zhejiang University China University of Illinois Urbana-Champaign United States Lawrence Livermore National Laboratory United States Alibaba Group

ISBN: (纸本)9781713821120

Recent advances in maximizing mutual information (MI) between the source and target have demonstrated its effectiveness in text generation. However, previous works paid little attention to modeling the backward network of MI (i.e. dependency from the target to the source), which is crucial to the tightness of the variational information maximization lower bound. In this paper, we propose Adversarial Mutual Information (AMI): a text generation framework which is formed as a novel saddle point (min-max) optimization aiming to identify joint interactions between the source and target. Within this framework, the forward and backward networks are able to iteratively promote or demote each other’s generated instances by comparing the real and synthetic data distributions. We also develop a latent noise sampling strategy that leverages random variations at the high-level semantic space to enhance the long term dependency in the generation process. Extensive experiments based on different text generation tasks demonstrate that the proposed AMI framework can significantly outperform several strong baselines, and we also show that AMI has potential to lead to a tighter lower bound of maximum mutual information for the variational information maximization problem. © 2020 37th International Conference on Machine Learning, ICML 2020. All rights reserved.

关键词： Semantics

Interactive Rendering of Relightable and Animatable Gaussian Avatars

学校读者我要写书评

暂无评论

IEEE Transactions on Visualization and computer Graphics 2025年

作者： Zhan, Youyi Shao, Tianjia Wang, He Yang, Yin Zhou, Kun Zhejiang University State Key Lab of CAD & CG Hangzhou310058 China University College London UCL Centre for Artificial Intelligence Department of Computer Science Gower Street LondonWC1E 6BT United Kingdom University of Utah Kahlert School of Computing United States

Creating relightable and animatable avatars from multi-view or monocular videos is a challenging task for digital human creation and virtual reality applications. Previous methods rely on neural radiance fields or ray tracing, resulting in slow training and rendering processes. By utilizing Gaussian Splatting, we propose a simple and efficient method to decouple body materials and lighting from sparse-view or monocular avatar videos, so that the avatar can be rendered simultaneously under novel viewpoints, poses, and lightings at interactive frame rates (6.9 fps). Specifically, we first obtain the canonical body mesh using a signed distance function and assign attributes to each mesh vertex. The Gaussians in the canonical space then interpolate from nearby body mesh vertices to obtain the attributes. We subsequently deform the Gaussians to the posed space using forward skinning, and combine the learnable environment light with the Gaussian attributes for shading computation. To achieve fast shadow modeling, we rasterize the posed body mesh from dense viewpoints to obtain the visibility. Our approach is not only simple but also fast enough to allow interactive rendering of avatar animation under environmental light changes. Experiments demonstrate that, compared to previous works, our method can render higher quality results at a faster speed on both synthetic and real datasets. © 1995-2012 IEEE.

关键词： Gaussian distribution

HAM:a deep collaborative ranking method incorporating textual information

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2020年第8期21卷 1206-1216页

作者： Cheng-wei WANG Teng-fei ZHOU Chen CHEN Tian-lei HU Gang CHEN The Key Laboratory of Big Data Intelligent Computing of Zhejiang Province Hangzhou 310027China State Key Lab of CAD&CG Zhejiang UniversityHangzhou 310027China College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China

The recommendation task with a textual corpus aims to model customer preferences from both user feedback and item textual *** is highly desirable to explore a very deep neural network to capture the complicated nonlinear ***,training a deeper recommender is not as effortless as simply adding layers.A deeper recommender suffers from the gradient vanishing/exploding issue and cannot be easily trained by gradient-based ***,textual descriptions probably contain noisy word *** extracting feature vectors from them can harm the recommender’s *** overcome these difficulties,we propose a new recommendation method named the HighwAy reco Mmender(HAM).HAM explores a highway mechanism to make gradient-based training methods stable.A multi-head attention mechanism is devised to automatically denoise textual ***,a block coordinate descent method is devised to train a deep neural *** studies show that the proposed method outperforms state-of-the-art methods significantly in terms of accuracy.

关键词： Deep learning Recommendation system Highway network Block coordinate descent

Do wider neural networks really help adversarial robustness? 21

学校读者我要写书评

暂无评论

Do wider neural networks really help adversarial robustness?

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Boxi Wu Jinghui Chen Deng Cai Xiaofei He Quanquan Gu State Key Lab of CAD & CG Zhejiang University Pennsylvania State University State College PA Dept. of Computer Science UCLA

ISBN: (纸本)9781713845393

Adversarial training is a powerful type of defense against adversarial examples. Previous empirical results suggest that adversarial training requires wider networks for better performances. However, it remains elusive how does neural network width affect model robustness. In this paper, we carefully examine the relationship between network width and model robustness. Specifically, we show that the model robustness is closely related to the tradeoff between natural accuracy and perturbation stability, which is controlled by the robust regularization parameter λ. With the same λ, wider networks can achieve better natural accuracy but worse perturbation stability, leading to a potentially worse overall model robustness. To understand the origin of this phenomenon, we further relate the perturbation stability with the network's local Lipschitzness. By leveraging recent results on neural tangent kernels, we theoretically show that wider networks tend to have worse perturbation stability. Our analyses suggest that: 1) the common strategy of first fine-tuning λ on small networks and then directly use it for wide model training could lead to deteriorated model robustness; 2) one needs to properly enlarge λ to unleash the robustness potential of wider models fully. Finally, we propose a new Width Adjusted Regularization (WAR) method that adaptively enlarges λ on wide models and significantly saves the tuning time.

关键词：

OpenSlot: Mixed Open-Set Recognition with Object-Centric Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yin, Xu Pan, Fei An, Guoyuan Huo, Yuchi Xie, Zixuan Yoon, Sung-Eui School of Computing Korea Advanced Institute of Science and Technology Daejeon34141 Korea Republic of School of Computer Science Engineering University of Michigan United States State Key Lab of CAD and CG Zhejiang University China Zhejiang Lab 310058 China Institute of Computing Technology University of Chinese Academy of Sciences Beijing100190 China Faculty of School of Computing Korea Advanced Institute of Science and Technology Deajeon34141 Korea Republic of

Existing open-set recognition (OSR) studies typically assume that each image contains only one class label, with the unknown test set (negative) having a disjoint label space from the known test set (positive), a scenario referred to as full-label shift. This paper introduces the mixed OSR problem, where test images contain multiple class semantics, with both known and unknown classes co-occurring in the negatives, leading to a more complex super-label shift that better reflects real-world scenarios. To tackle this challenge, we propose the OpenSlot framework, based on object-centric learning, which uses slot features to represent diverse class semantics and generate class predictions. The proposed anti-noise slot (ANS) technique helps mitigate the impact of noise (invalid or background) slots during classification training, addressing the semantic misalignment between class predictions and ground truth. We evaluate OpenSlot on both mixed and conventional OSR benchmarks. Without elaborate designs, our method not only excels existing approaches in detecting super-label shifts across OSR tasks, but also achieves state-of-the-art performance on conventional benchmarks. Meanwhile, OpenSlot can localize class objects without using bounding boxes during training, demonstrating competitive performance in open-set object detection and potential for generalization. © 2024, CC BY-NC-ND.

关键词： Object detection

AtlasSeg: Atlas Prior Guided Dual-U-Net for Tissue Segmentation in Fetal Brain MRI

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Haoan Zheng, Tianshu Xu, Xinyi Shen, Yao Sun, Jiwei Sun, Cong Wang, Guangbin Cui, Zhaopeng Wu, Dan Key Laboratory for Biomedical Engineering of Ministry of Education Department of Biomedical Engineering College of Biomedical Engineering & Instrument Science Zhejiang University Hangzhou310027 China Department of Radiology Beijing Hospital National Center of Gerontology Institute of Geriatric Medicine Chinese Academy of Medical Sciences Beijing100730 China Department of Radiology Shandong Provincial Hospital Affiliated to Shandong First Medical University Shandong Jinan276899 China State Key Lab of CAD&CG Zhejiang University Hangzhou China

Objective: Accurate automatic tissue segmentation in fetal brain MRI is a crucial step in clinical diagnosis but remains challenging, particularly due to the dynamically changing anatomy and tissue contrast during fetal development. Existing segmentation networks can only implicitly learn age-related features, leading to a decline in accuracy at extreme early or late gestational ages (GAs). Methods: To improve segmentation performance throughout gestation, we introduce AtlasSeg, a dual-U-shape convolution network that explicitly integrates GA-specific information as guidance. By providing a publicly available fetal brain atlas with segmentation labels corresponding to relevant GAs, AtlasSeg effectively extracts age-specific patterns in the atlas branch and generates precise tissue segmentation in the segmentation branch. Multi-scale spatial attention feature fusions are constructed during both encoding and decoding stages to enhance feature flow and facilitate better information interactions between two branches. Results: We compared AtlasSeg with six well-established networks in a seven-tissue segmentation task, achieving the highest average Dice similarity coefficient of 0.91. The improvement was particularly evident in extreme early or late GA cases, where training data was scare. Furthermore, AtlasSeg exhibited minimal performance degradation on low-quality images with contrast changes and noise, attributed to its anatomical shape priors. Conclusion: AtlasSeg demonstrated enhanced segmentation accuracy, better consistency across fetal ages, and robustness to perturbations, making it a powerful tool for reliable fetal brain MRI tissue segmentation, particularly suited for diagnostic assessments during early gestation. Copyright © 2024, The Authors. All rights reserved.

关键词： Tissue