Adaptive Clustering and Weighted Regularization Contrastive Learning Framework for Unsupervised Person Re-Identification
Mingfu Xionga, Kaikang Hua, Zhongyuan Wangb c, Ruimin Hub c, Khan Muhammadd, Javier Del Sere, Xiaokang Yangf g, Bin Shengh i
- aSchool of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, China
- bComputer Science and the School of Cyber Science and Engineering, Wuhan University, Wuhan, China
- cSchool of Computer Science, Wuhan University, Wuhan, China
- dVisual Analytics for Knowledge Laboratory (VIS2KNOW Lab), Department of Applied Artificial Intelligence, School of Convergence, College of Computing and Informatics, Sungkyunkwan University, Seoul, Republic of Korea
- eTECNALIA, Basque Research and Technology Alliance (BRTA), Derio, Spain
- fMOE Key Laboratory of AI, School of Electronics Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China
- gMOE Key Laboratory of AI, School of Electronics, Information, and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China
- hDepartment of Computer Science and Engineering, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
Unsupervised person re-identification (ReID) has recently gained significant attention from researchers. ReID matches images of the same person from different camera views in various scenes without any labels. Existing clustering methods primarily rely on a fixed threshold (the maximum distance between sample points and clustering centroids) and overlook the importance of adjusting this threshold during continuous model optimization. This mismatch between clustering thresholds and inter- or intra-class spacing reduces clustering accuracy. To address this issue, this study proposes an Adaptive Clustering and Weighted Regularization Contrastive Learning (ACWRCL) framework for unsupervised person ReID. The ACWRCL framework comprises two main components: (1) the Clustering Threshold Adaptive Adjustment (CTAA) module, and (2) the Weighted Regularization Contrastive Learning (WRCL) module. The CTAA module dynamically adjusts the clustering threshold to align with model optimization, ensuring that the threshold remains within an appropriate range to prevent under- or over-robustness in the clustering model. The WRCL module uses the similarity ratio between the query sample and the clustering centroid relative to the overall similarity of all samples with the same labels as the query sample. This ratio is used as the weight in the loss function to penalize incorrect clustering and improve pseudo-label generation accuracy. Extensive experiments on public ReID datasets—Market-1501, MSMT17, Veri776, CUHK03, and PersonX—demonstrate the effectiveness of the proposed method.