Multi-Centroid Representation Network for Domain Adaptive Person Re-ID

• Published in: Proceedings of the ... AAAI Conference on Artificial Intelligence 2022-06, Vol.36 (3), p.2750-2758
• Main Authors: Wu, Yuhang, Huang, Tengteng, Yao, Haotian, Zhang, Chi, Shao, Yuanjie, Han, Chuchu, Gao, Changxin, Sang, Nong
• Format: Article
• Language: English
• ISSN: 2159-5399; 2374-3468
• DOI: 10.1609/aaai.v36i3.20178

Recently, many approaches tackle the Unsupervised Domain Adaptive person re-identification (UDA re-ID) problem through pseudo-label-based contrastive learning. During training, a uni-centroid representation is obtained by simply averaging all the instance features from a cluster with the same pseudo label. However, a cluster may contain images with different identities (label noises) due to the imperfect clustering results, which makes the uni-centroid representation inappropriate. In this paper, we present a novel Multi-Centroid Memory (MCM) to adaptively capture different identity information within the cluster. MCM can effectively alleviate the issue of label noises by selecting proper positive/negative centroids for the query image. Moreover, we further propose two strategies to improve the contrastive learning process. First, we present a Domain-Specific Contrastive Learning (DSCL) mechanism to fully explore intra-domain information by comparing samples only from the same domain. Second, we propose Second-Order Nearest Interpolation (SONI) to obtain abundant and informative negative samples. We integrate MCM, DSCL, and SONI into a unified framework named Multi-Centroid Representation Network (MCRN). Extensive experiments demonstrate the superiority of MCRN over state-of-the-art approaches on multiple UDA re-ID tasks and fully unsupervised re-ID tasks.