检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Yang, Guang Liu, Wu Liu, Xinchen Gu, Xiaoyan Cao, Juan Li, Jintao Institute of Computing Technology Chinese Academy of Sciences China Jd Explore Academy Institute of Information Engineering Chinese Academy of Sciences China The Key Lab of Intelligent Information Processing of Chinese Academy of Sciences The University of Chinese Academy of Sciences China

Human motion transfer refers to synthesizing photo-realistic and temporally coherent videos that enable one person to imitate the motion of others. However, current synthetic videos suffer from the temporal inconsistency in sequential frames that significantly degrades the video quality, yet is far from solved by existing methods in the pixel domain. Recently, some works on DeepFake detection try to distinguish the natural and synthetic images in the frequency domain because of the frequency insufficiency of image synthesizing methods. Nonetheless, there is no work to study the temporal inconsistency of synthetic videos from the aspects of the frequency-domain gap between natural and synthetic videos. Therefore, in this paper, we propose to delve into the frequency space for temporally consistent human motion transfer. First of all, we make the first comprehensive analysis of natural and synthetic videos in the frequency domain to reveal the frequency gap in both the spatial dimension of individual frames and the temporal dimension of the video. To close the frequency gap between the natural and synthetic videos, we propose a novel Frequency-based human MOtion TRansfer framework, named FreMOTR, which can effectively mitigate the spatial artifacts and the temporal inconsistency of the synthesized videos. FreMOTR explores two novel frequency-based regularization modules: 1) the Frequency-domain Appearance Regularization (FAR) to improve the appearance of the person in individual frames and 2) Temporal Frequency Regularization (TFR) to guarantee the temporal consistency between adjacent frames. Finally, comprehensive experiments demonstrate that the FreMOTR not only yields superior performance in temporal consistency metrics but also improves the frame-level visual quality of synthetic videos. In particular, the temporal consistency metrics are improved by nearly 30% than the state-of-the-art model. © 2022, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Rapidly Solving Wideband RCS by Combining UCBFM and Compressive Sensing

引用

Progress In Electromagnetics Research C 2022年 124卷 33-42页

作者： Wang, Zhonggen Li, Chenwei Sun, Yufa Nie, Wenyan Wang, Pan Lin, Han School of Electrical and Information Engineering Anhui University of Science and Technology Huainan232001 China Key Lab of Intelligent Computing & Signal Processing Anhui University Hefei230039 China School of Mechanical and Electrical Engineering Huainan Normal University Huainan232001 China

While analyzing wideband electromagnetic scattering problems using ultra-wideband characteristic basis function method (UCBFM), the reconstruction of a reduced matrix and the recalculation of an impedance matrix at each frequency point cost a large amount of time. To overcome this issue, a novel method that combines UCBFM with compressive sensing (CS) is proposed in this paper to rapidly analyse the wideband RCS. The proposed method makes the ultra-wideband characteristic basis functions (UCBFs) generated at the highest frequency as the sparse basis, introduces the CS theory, randomly extracts several rows from the original matrix as the measurement matrix, utilizes the corresponding excitation vector as the measurement value, and then employs the recovery algorithm, through which the solution of target induced current can be obtained. Due to partial filling of impedance matrix and efficient recovery algorithm, the wideband RCS computation time of the object is significantly reduced using the proposed method. Furthermore, the numerical simulation results show that the computation efficiency for the target wideband RCS can be further enhanced compared with that of the stand-alone UCBFM. © 2022, Electromagnetics Academy. All rights reserved.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Boosting the Transferability of Video Adversarial Examples via Temporal Translation

arXiv

引用

arXiv 2021年

作者： Wei, Zhipeng Chen, Jingjing Wu, Zuxuan Jiang, Yu-Gang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China

Although deep-learning based video recognition models have achieved remarkable success, they are vulnerable to adversarial examples that are generated by adding human-imperceptible perturbations on clean video samples. As indicated in recent studies, adversarial examples are transferable, which makes it feasible for black-box attacks in real-world applications. Nevertheless, most existing adversarial attack methods have poor transferability when attacking other video models and transfer-based attacks on video models are still unexplored. To this end, we propose to boost the transferability of video adversarial examples for black-box attacks on video recognition models. Through extensive analysis, we discover that different video recognition models rely on different discriminative temporal patterns, leading to the poor transferability of video adversarial examples. This motivates us to introduce a temporal translation attack method, which optimizes the adversarial perturbations over a set of temporal translated video clips. By generating adversarial examples over translated videos, the resulting adversarial examples are less sensitive to temporal patterns existed in the white-box model being attacked and thus can be better transferred. Extensive experiments on the Kinetics-400 dataset and the UCF-101 dataset demonstrate that our method can significantly boost the transferability of video adversarial examples. For transfer-based attack against video recognition models, it achieves a 61.56% average attack success rate on the Kinetics-400 and 48.60% on the UCF-101. Code is available at https://***/zhipeng-wei/TT. © 2021, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Attacking Video Recognition Models with Bullet-Screen Comments

arXiv

引用

arXiv 2021年

作者： Chen, Kai Wei, Zhipeng Chen, Jingjing Wu, Zuxuan Jiang, Yu-Gang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China

Recent research has demonstrated that Deep Neural Networks (DNNs) are vulnerable to adversarial patches which introduce perceptible but localized changes to the input. Nevertheless, existing approaches have focused on generating adversarial patches on images, their counterparts in videos have been less explored. Compared with images, attacking videos is much more challenging as it needs to consider not only spatial cues but also temporal cues. To close this gap, we introduce a novel adversarial attack in this paper, the bullet-screen comment (BSC) attack, which attacks video recognition models with BSCs. Specifically, adversarial BSCs are generated with a Reinforcement Learning (RL) framework, where the environment is set as the target model and the agent plays the role of selecting the position and transparency of each BSC. By continuously querying the target models and receiving feedback, the agent gradually adjusts its selection strategies in order to achieve a high fooling rate with non-overlapping BSCs. As BSCs can be regarded as a kind of meaningful patch, adding it to a clean video will not affect people's understanding of the video content, nor will arouse people's suspicion. We conduct extensive experiments to verify the effectiveness of the proposed method. On both UCF-101 and HMDB-51 datasets, our BSC attack method can achieve about 90% fooling rate when attacking three mainstream video recognition models, while only occluding © 2021, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Harnessing Hierarchical label Distribution Variations in Test Agnostic Long-tail Recognition

arXiv

引用

arXiv 2024年

作者： Yang, Zhiyong Xu, Qianqian Wang, Zitai Li, Sicong Han, Boyu Bao, Shilong Cao, Xiaochun Huang, Qingming School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS Institute of Information Engineering CAS School of Cyber Security University of Chinese Academy of Sciences China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China BDKM University of Chinese Academy of Sciences China

This paper explores test-agnostic long-tail recognition, a challenging long-tail task where the test label distributions are unknown and arbitrarily imbalanced. We argue that the variation in these distributions can be broken down hierarchically into global and local levels. The global ones reflect a broad range of diversity, while the local ones typically arise from milder changes, often focused on a particular neighbor. Traditional methods predominantly use a Mixture-of-Expert (MoE) approach, targeting a few fixed test label distributions that exhibit substantial global variations. However, the local variations are left unconsidered. To address this issue, we propose a new MoE strategy, DirMixE, which assigns experts to different Dirichlet meta-distributions of the label distribution, each targeting a specific aspect of local variations. Additionally, the diversity among these Dirichlet meta-distributions inherently captures global variations. This dual-level approach also leads to a more stable objective function, allowing us to sample different test distributions better to quantify the mean and variance of performance outcomes. Theoretically, we show that our proposed objective benefits from enhanced generalization by virtue of the variance-based regularization. Comprehensive experiments across multiple benchmarks confirm the effectiveness of DirMixE. The code is available at https: //***/scongl/DirMixE. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features

arXiv

引用

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at this url. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

CREAM: Weakly Supervised Object Localization via Class RE-Activation Mapping

arXiv

引用

arXiv 2022年

作者： Xu, Jilan Hou, Junlin Zhang, Yuejie Feng, Rui Zhao, Rui-Wei Zhang, Tao Lu, Xuequan Gao, Shang School of Computer Science Shanghai Key Lab of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China Academy for Engineer and Technology Fudan University China Shanghai University of Finance and Economics China Deakin University Australia

Weakly Supervised Object Localization (WSOL) aims to localize objects with image-level supervision. Existing works mainly rely on Class Activation Mapping (CAM) derived from a classification model. However, CAM-based methods usually focus on the most discriminative parts of an object (i.e., incomplete localization problem). In this paper, we empirically prove that this problem is associated with the mixup of the activation values between less discriminative foreground regions and the background. To address it, we propose Class RE-Activation Mapping (CREAM), a novel clustering-based approach to boost the activation values of the integral object regions. To this end, we introduce class-specific foreground and background context embeddings as cluster centroids. A CAM-guided momentum preservation strategy is developed to learn the context embeddings during training. At the inference stage, the re-activation mapping is formulated as a parameter estimation problem under Gaussian Mixture Model, which can be solved by deriving an unsupervised Expectation-Maximization based soft-clustering algorithm. By simply integrating CREAM into various WSOL approaches, our method significantly improves their performance. CREAM achieves the state-of-the-art performance on CUB, ILSVRC and OpenImages benchmark datasets. Code will be available at https://***/Jazzcharles/CREAM. © 2022, CC BY.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques

arXiv

引用

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at this url. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The minority matters: a diversity-promoting collaborative metric learning algorithm 22

The minority matters: a diversity-promoting collaborative me...

引用

Proceedings of the 36th International Conference on Neural information processing Systems

作者： Shilong Bao Qianqian Xu Zhiyong Yang Yuan He Xiaochun Cao Qingming Huang State Key Laboratory of Information Security Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Computer Science and Tech. University of Chinese Academy of Sciences Alibaba Group School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Laboratory of Big Data Mining and Knowledge Management CAS and Peng Cheng Laboratory

ISBN: (纸本)9781713871088

Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collaborative Filtering. Following the convention of RS, existing methods exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, we argue that the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collaborative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to include a multiple set of representations for each user in the system. Based on this embedding paradigm, user preference toward an item is aggregated from different embeddings by taking the minimum item-user distance among the user embedding set. Furthermore, we observe that the diversity of the embeddings for the same user also plays an essential role in the model. To this end, we propose a Diversity Control Regularization Scheme (DCRS) to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could generalize well to unseen test data by tackling the challenge of the annoying operation that comes from the minimum value. Experiments over a range of benchmark datasets speak to the efficacy of DPCML.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Revisiting Adversarial Robustness Distillation: Robust Soft labels Make Student Better

Revisiting Adversarial Robustness Distillation: Robust Soft ...

引用

International Conference on Computer Vision (ICCV)

作者： Bojia Zi Shihao Zhao Xingjun Ma Yu-Gang Jiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan Univeristy Shanghai Collaborative Innovation Center on Intelligent Visual Computing School of Information Technology Deakin University Geelong Australia

ISBN: (纸本)9781665428132

Adversarial training is one effective approach for training robust deep neural networks against adversarial attacks. While being able to bring reliable robustness, adversarial training (AT) methods in general favor high capacity models, i.e., the larger the model the better the robustness. This tends to limit their effectiveness on small models, which are more preferable in scenarios where storage or computing resources are very limited (e.g., mobile devices). In this paper, we leverage the concept of knowledge distillation to improve the robustness of small models by distilling from adversarially trained large models. We first revisit several state-of-the-art AT methods from a distillation perspective and identify one common technique that can lead to improved robustness: the use of robust soft labels – predictions of a robust model. Following this observation, we propose a novel adversarial robustness distillation method called Robust Soft label Adversarial Distillation (RSLAD) to train robust small student models. RSLAD fully exploits the robust soft labels produced by a robust (adversarially-trained) large teacher model to guide the student’s learning on both natural and adversarial examples in all loss terms. We empirically demonstrate the effectiveness of our RSLAD approach over existing adversarial training and distillation methods in improving the robustness of small models against state-of-the-art attacks including the AutoAttack. We also provide a set of understandings on our RSLAD and the importance of robust soft labels for adversarial robustness distillation. Code: https://***/zibojia/RSLAD.

关键词： Training Deep learning Computer vision Codes Computational modeling Neural networks Predictive models

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：