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. 智能感知与计算研究中心
Learning Domain Invariant Representations for Generalizable Person Re-Identification

文献类型：期刊论文

作者Zhang, Yi-Fan4,5; Zhang, Zhang4,5; Li, Da4,5; Jia, Zhen4,5; Wang, Liang1,2,3; Tan, Tieniu1,2,3
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2023
卷号32页码:509-523
ISSN号1057-7149
关键词Generalizable person re-Identification disentanglement backdoor adjustment
DOI10.1109/TIP.2022.3229621
通讯作者Zhang, Zhang(zzhang@nlpr.ia.ac.cn)
英文摘要Generalizable person Re-Identification (ReID) aims to learn ready-to-use cross-domain representations for direct cross-data evaluation, which has attracted growing attention in the recent computer vision (CV) community. In this work, we construct a structural causal model (SCM) among identity labels, identity-specific factors (clothing/shoes color etc.), and domain-specific factors (background, viewpoints etc.). According to the causal analysis, we propose a novel Domain Invariant Representation Learning for generalizable person Re-Identification (DIR-ReID) framework. Specifically, we propose to disentangle the identity-specific and domain-specific factors into two independent feature spaces, based on which an effective backdoor adjustment approximate implementation is proposed for serving as a causal intervention towards the SCM. Extensive experiments have been conducted, showing that DIR-ReID outperforms state-of-the-art (SOTA) methods on large-scale domain generalization (DG) ReID benchmarks.
WOS关键词NETWORK
资助项目National Natural Science Foundation of China[62106260] ; National Natural Science Foundation of China[62236010] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[U1803261] ; China Postdoctoral Science Foundation[2020M680751]
WOS研究方向Computer Science ; Engineering
语种英语
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号WOS:000906943400004
资助机构National Natural Science Foundation of China ; China Postdoctoral Science Foundation
源URL[http://ir.ia.ac.cn/handle/173211/51347]  
专题自动化研究所_智能感知与计算研究中心
多模态人工智能系统全国重点实验室
通讯作者Zhang, Zhang
作者单位1.Univ Chinese Acad Sci UCAS, Sch Artificial Intelligence, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100044, Peoples R China
3.Chinese Acad Sci CASIA, Inst Automat, Ctr Res Intelligent Percept & Comp, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
4.Univ Chinese Acad Sci UCAS, Sch Artificial Intelligence, Beijing 100049, Peoples R China
5.Chinese Acad Sci CASIA, Inst Automat, Ctr Res Intelligent Percept & Comp CRIPAC, Natl Lab Pattern Recognit NLPR, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Yi-Fan,Zhang, Zhang,Li, Da,et al. Learning Domain Invariant Representations for Generalizable Person Re-Identification[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2023,32:509-523.
APA Zhang, Yi-Fan,Zhang, Zhang,Li, Da,Jia, Zhen,Wang, Liang,&Tan, Tieniu.(2023).Learning Domain Invariant Representations for Generalizable Person Re-Identification.IEEE TRANSACTIONS ON IMAGE PROCESSING,32,509-523.
MLA Zhang, Yi-Fan,et al."Learning Domain Invariant Representations for Generalizable Person Re-Identification".IEEE TRANSACTIONS ON IMAGE PROCESSING 32(2023):509-523.

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。