中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
Exponential Information Bottleneck Theory Against Intra-Attribute Variations for Pedestrian Attribute Recognition

文献类型：期刊论文

作者Wu, Junyi4,5; Huang, Yan6; Gao, Min7; Gao, Zhipeng4; Zhao, Jianqiang4; Shi, Jieming8; Zhang, Anguo1,2,3,8
刊名IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
出版日期2023
卷号18页码:5623-5635
关键词Feature extraction Pedestrians Mutual information Body regions Training Task analysis Semantics Pedestrian attribute recognition intra-attribute variations exponential information bottleneck
ISSN号1556-6013
DOI10.1109/TIFS.2023.3311584
通讯作者Huang, Yan(yan.huang@cripac.ia.ac.cn) ; Zhang, Anguo(anguo.zhang@hotmail.com)
英文摘要Multi-label pedestrian attribute recognition (PAR) involves assigning multiple attributes to pedestrian images captured by video surveillance cameras. Despite its importance, learning robust attribute-related features for PAR remains a challenge due to the large intra-attribute variations in the image space. These variations, which stem from changes in pedestrian poses, illumination conditions, and background noise, make extracted attribute-related features susceptible to irrelevant information or noise interference. Existing PAR methods rely on body prior extractors or attention mechanisms to locate attribute-correlation regions for extracting robust features. However, these methods may not be robust to intra-attribute variations, which limits their effectiveness. To address this challenge, we propose a novel and flexible PAR framework that leverages the exponential information bottleneck (ExpIB) approach. Our ExpIB-Net uses mutual information compression as the main penalty during the early stage of training, thereby eliminating irrelevant information. As training progresses, the mutual information penalty weakens and the Binary Cross-Entropy Loss (BCELoss) contributes to improving the PAR recognition accuracy. Our method can also be integrated into an attention module to form the AttExpIB-Net, which better handles intra-attribute variations for better performance. Additionally, our model-agnostic ExpIB approach is plug-and-play, requiring no additional computational overhead during inference. Experiments on several challenging PAR datasets show that our method outperforms state-of-the-art approaches.
WOS关键词PERSON REIDENTIFICATION ; ATTENTION NETWORK
资助项目National Natural Science Foundation of China[62306311] ; Fellowship of China Post-Doctoral Science Foundation[62306001] ; International Post-Doctoral Exchange Fellowship Program (Talent-Introduction Program) of China[2022T150698] ; Special Research Assistant Program of the Chinese Academy of Sciences[YJ20210324] ; Public Security Artificial Intelligence Infrastructure Support Platform ; [E2S9180301]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001070669000003
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Natural Science Foundation of China ; Fellowship of China Post-Doctoral Science Foundation ; International Post-Doctoral Exchange Fellowship Program (Talent-Introduction Program) of China ; Special Research Assistant Program of the Chinese Academy of Sciences ; Public Security Artificial Intelligence Infrastructure Support Platform
源URL[http://ir.ia.ac.cn/handle/173211/53125]  
专题多模态人工智能系统全国重点实验室
通讯作者Huang, Yan; Zhang, Anguo
作者单位1.Anhui Univ, Sch Artificial Intelligence, Hefei 230039, Peoples R China
2.Minist Educ, Res Ctr Autonomous Unmanned Syst Technol, Hefei 230030, Peoples R China
3.Anhui Prov Engn Res Ctr Unmanned Syst & Intellige, Hefei 230039, Peoples R China
4.Xiamen Meiya Pico Informat Co Ltd, AI Res Ctr, Xiamen 361000, Peoples R China
5.Xiamen Meiya Pico Informat Secur Res Inst Co Ltd, Xiamen 361000, Peoples R China
6.Chinese Acad Sci CASIA, Ctr Res Intelligent Percept & Comp CRIPAC, Inst Automat, Natl Lab Pattern Recognit NLPR, Beijing 100190, Peoples R China
7.Fuzhou Univ, Coll Phys & Informat Engn, Fujian Key Lab Intelligent Proc & Wireless Transm, Fuzhou 350002, Peoples R China
8.Hong Kong Polytech Univ, Dept Comp, Hong Kong, Peoples R China
推荐引用方式
GB/T 7714		 Wu, Junyi,Huang, Yan,Gao, Min,et al. Exponential Information Bottleneck Theory Against Intra-Attribute Variations for Pedestrian Attribute Recognition[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2023,18:5623-5635.
APA Wu, Junyi.,Huang, Yan.,Gao, Min.,Gao, Zhipeng.,Zhao, Jianqiang.,...&Zhang, Anguo.(2023).Exponential Information Bottleneck Theory Against Intra-Attribute Variations for Pedestrian Attribute Recognition.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,18,5623-5635.
MLA Wu, Junyi,et al."Exponential Information Bottleneck Theory Against Intra-Attribute Variations for Pedestrian Attribute Recognition".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 18(2023):5623-5635.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。