南京邮电大学学报（自然科学版）2024，Vol.44Issue(3)：63-71,9.DOI:10.14132/j.cnki.1673-5439.2024.03.008
基于动态辅助对比学习的跨域行人重识别
Dynamic auxiliary contrastive learning for cross-domain person re-identification
摘要
Abstract
The self-paced contrastive learning(SpCL)with hybrid memory uses clustering to train the network to generate different levels of pseudo labels,and achieves good re-identification results.However,as a distribution difference exists between the pedestrian datasets captured from the source domain and the target domain,the trained network cannot accurately identify the features of the target domain and the source domain.To solve this problem,this paper proposes a two-branch dynamic auxiliary contrastive learning(DACL)framework.This framework effectively learns the domain invariant features of the target domain by dynamically reducing the local maximum mean discrepancy(LMMD)between the source domain and the target domain.In addition,the generalized mean(GeM)pooling strategy is adopted to aggregate features after feature extraction,so that the proposed network can adaptively aggregate the important features in the image space.Finally,simulation experiments are conducted on three classic person re-identification datasets.Compared with the unsupervised domain adaptation for person re-identification methods with the second best performance,the proposed DACL increases mAP and rank-1 by 6.0 percentages and 2.2 percentages on the Market1501 dataset,2.8 percentages and 3.6 percentages on the MSMT17 dataset,and 1.7 percentages and 2.1 percentages on the Duke dataset,respectively.关键词
行人重识别/无监督域自适应/广义均值池化/局部最大平均差异/对比学习Key words
person re-identification(ReID)/unsupervised domain adaptation(UDA)/generalized mean(Gem)pooling/local maximum mean discrepancy(LMMD)/contrastive learning分类
信息技术与安全科学引用本文复制引用
杨真真,邵静,杨永鹏,吴心怡..基于动态辅助对比学习的跨域行人重识别[J].南京邮电大学学报（自然科学版）,2024,44(3):63-71,9.基金项目
国家自然科学基金(62071242,62171232)、江苏省研究生科研与实践创新计划项目(KYCX22_0955,SJCX23_0251)和南京邮电大学科研项目(NY220207)资助项目 （62071242,62171232）
