Domain Adaptive Learning with Multi‐Granularity Features for Unsupervised Person Re‐identification. Issue 1 (1st January 2022)

• Record Type: Journal Article
• Authors: FU, Lihua; DU, Yubin; DING, Yu; WANG, Dan; JIANG, Hanxu; ZHANG, Haitao
• Is Part Of: Chinese journal of electronics. Volume 31:Issue 1(2022)
• Page Start: 116
• Page End: 128
• Publication Date: 2022-01-01
• Subjects: Person re‐identification -- Deep learning -- Multi‐granularity -- Domain adaptive; Electronics -- Periodicals; Electronics -- China -- Periodicals; Electronics; China; Periodicals; 621.38105
• DOI: 10.1049/cje.2020.00.072
• Languages: English
• ISSNs: 1022-4653

Abstract

Abstract : Unsupervised person re‐identification (Re‐ID) aims to improve the model's scalability and obtain better Re‐ID results in the unlabeled data domain. In this paper, we propose an unsupervised person Re‐ID method based on multi‐granularity feature representation and domain adaptive learning, which can effectively improve the performance of unsupervised person re‐identification. The multi‐granularity feature extraction module integrates global and local information of different granularity to obtain the multi‐granularity person feature representation with rich discriminative information. The source domain classification module learns the labeled source dataset classification and obtains the person's discriminative knowledge in the source domain. On this basis, the domain adaptive module further considers the difference between the target domain and the source domain to learn adaptively for the model. Experiments on multiple public datasets show that the proposed method can achieve a competitive performance among other state‐of‐the‐art unsupervised Re‐ID methods.