文献类型：期刊文献

英文题名：Asymmetric Mutual Mean-Teaching for Unsupervised Domain Adaptive Person Re-Identification

作者：Dong, Yachao[1];Liu, Hongzhe[1];Xu, Cheng[1]

第一作者：Dong, Yachao

通讯作者：Liu, HZ[1]

机构：[1]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China

第一机构：北京联合大学北京市信息服务工程重点实验室

通讯机构：[1]corresponding author), Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China.|[11417103]北京联合大学北京市信息服务工程重点实验室;[11417]北京联合大学;

年份：2021

卷号：9

起止页码：69971-69984

外文期刊名：IEEE ACCESS

收录：;EI(收录号：20212110387598);Scopus(收录号：2-s2.0-85107227256);WOS:【SCI-EXPANDED(收录号:WOS:000650473000001)】；

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 61871039, Grant 61906017, and Grant 61802019; in part by the Beijing Municipal Commission of Education Project under Grant KM202111417001 and Grant KM201911417001; in part by the National Engineering Laboratory for Agri-Product Quality Traceability Project under Grant AQT-2020-YB2; in part by the Collaborative Innovation Center for Visual Intelligence under Grant CYXC2011; in part by the Academic Research Projects of Beijing Union University under Grant ZB10202003, Grant ZK80202001, Grant XP202015, and Grant BPHR2019AZ01; and in part by the Beijing Union University Graduate Research and Innovation Funding Project under Grant YZ2020K001.

语种：英文

外文关键词：Feature extraction; Adaptation models; Training; Task analysis; Generative adversarial networks; Clustering algorithms; Unsupervised learning; Deep learning; person re-identification; unsupervised domain adaptation; mutual mean-teaching

摘要：Unsupervised domain adaptive person re-identification aims to solve the problem of poor performance caused by transferring an unlabeled target domain from the labeled source domain in the re-identification task. The clustering pseudo-labels method in unsupervised learning is widely used in unsupervised adaptive person re-identification tasks, and it maintains state-of-the-art performance. However, pseudo-labels obtained through clustering often have much noise, and the use of a single network model structure and a single clustering algorithm can easily cause model learning to stagnate, making the model not generalizable. To solve this problem, this paper proposes an asymmetric mutual mean-teaching method for unsupervised adaptive person re-identification. In terms of feature extraction, two asymmetric network models with different structures are used for mutual mean-teaching on the target domain, making the features extracted by the network more robust. In terms of feature clustering, two clustering methods are used for mutual teaching to dynamically update the centroid of clusters to improve the confidence of clustering pseudo-labels. Finally, the triplet loss is improved based on the updated cluster centroid to improve the clustering effect. The proposed method is used to perform a large number of verification experiments on three public datasets. The experimental results show that the proposed method has better accuracy than other unsupervised person re-identification based on clustering pseudo-labels.