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. 紫东太初大模型研究中心
  5. 图像与视频分析团队
Pseudo Label Rectification With Joint Camera Shift Adaptation and Outlier Progressive Recycling for Unsupervised Person Re-Identification

文献类型：期刊论文

作者Xu, Mingyuan6; Guo, Haiyun4,5; Jia, Yuheng2,3; Dai, Zhitao6; Wang, Jinqiao1,4
刊名IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
出版日期2022-11-30
页码12
ISSN号1524-9050
关键词Person re-identification unsupervised learning domain adaptation pseudo label rectification
DOI10.1109/TITS.2022.3224233
通讯作者Guo, Haiyun(haiyun.guo@nlpr.ia.ac.cn) ; Jia, Yuheng(yhjia@seu.edu.cn)
英文摘要Person re-identification (re-ID) has many applications in intelligent transportation systems. Clustering-based methods, which alternate between the generation of pseudo labels via clustering and the optimization of the feature extractor, have obtained leading performance in unsupervised person re-ID. But there are still two issues not well addressed: 1) Most methods measure the feature similarity without considering the domain shift between cameras, degrading the clustering performance. 2) Outliers, which usually correspond to hard samples with large discrepancy from other images of the identical person, are in most cases directly excluded from the network training. To tackle the above issues, this paper proposes a plug-and-play pseudo label rectification framework, which jointly utilizes CAmera Shift adapTation module and Outlier progressive Recycling strategy ( $CASTOR$ ) to improve the quality of pseudo labels from both pre-clustering and post-clustering. Specifically, we first compute the camera similarity of two samples by utilizing a pretrained camera classification network and subtract the feature similarity by the camera similarity, the value of which is weighted in an exponential decay manner throughout the network training, in order to adaptively remedy the adverse impact of inter-camera distribution shift upon clustering. Besides, we carefully design an outlier progressive recycling strategy to reassign part of the outliers into the clustered groups to make full use of the useful information of outliers. Extensive experiments on three large scale unsupervised and unsupervised domain adaptive (UDA) person re-ID benchmarks validate the effectiveness of CASTOR and its wide compatibility with the state-of-the-art clustering-based methods.
资助项目National Key Research and Development Program of China[2021ZD0110403] ; National Natural Science Foundation of China[62002356] ; National Natural Science Foundation of China[62106044] ; National Natural Science Foundation of China[62002357] ; National Natural Science Foundation of China[62076235] ; Natural Science Foundation of Jiangsu Province[BK20210221] ; Zhejiang Laboratory[2021KH0AB07]
WOS研究方向Engineering ; Transportation
语种英语
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号WOS:000912859500001
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China ; Natural Science Foundation of Jiangsu Province ; Zhejiang Laboratory
源URL[http://ir.ia.ac.cn/handle/173211/51066]  
专题自动化研究所_模式识别国家重点实验室_图像与视频分析团队
通讯作者Guo, Haiyun; Jia, Yuheng
作者单位1.Peng Cheng Lab, Shenzhen 518066, Peoples R China
2.Southeast Univ, Sch Comp Sci & Engn, Nanjing 210096, Peoples R China
3.Southeast Univ, Key Lab Comp Network & Informat Integrat, Minist Educ, Nanjing 210096, Peoples R China
4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100864, Peoples R China
5.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China
6.Beijing Univ Posts & Telecommun, Sch Comp Sci, Beijing 100864, Peoples R China
推荐引用方式
GB/T 7714		 Xu, Mingyuan,Guo, Haiyun,Jia, Yuheng,et al. Pseudo Label Rectification With Joint Camera Shift Adaptation and Outlier Progressive Recycling for Unsupervised Person Re-Identification[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2022:12.
APA Xu, Mingyuan,Guo, Haiyun,Jia, Yuheng,Dai, Zhitao,&Wang, Jinqiao.(2022).Pseudo Label Rectification With Joint Camera Shift Adaptation and Outlier Progressive Recycling for Unsupervised Person Re-Identification.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,12.
MLA Xu, Mingyuan,et al."Pseudo Label Rectification With Joint Camera Shift Adaptation and Outlier Progressive Recycling for Unsupervised Person Re-Identification".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022):12.

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。