Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification
This work addresses a challenging and under-explored problem in cross-modal person re-identification for surveillance applications, offering an incremental improvement over existing methods.
The paper tackles unsupervised visible-infrared person re-identification by addressing the limitation of cluster-based methods that focus only on commonality, proposing a method that emphasizes divergence and variety through hard and dynamic prototypes, achieving state-of-the-art results on SYSU-MM01 and RegDB datasets.
Unsupervised visible-infrared person re-identification (USVI-ReID) aims to match specified people in infrared images to visible images without annotations, and vice versa. USVI-ReID is a challenging yet under-explored task. Most existing methods address the USVI-ReID using cluster-based contrastive learning, which simply employs the cluster center as a representation of a person. However, the cluster center primarily focuses on commonality, overlooking divergence and variety. To address the problem, we propose a Progressive Contrastive Learning with Hard and Dynamic Prototypes method for USVI-ReID. In brief, we generate the hard prototype by selecting the sample with the maximum distance from the cluster center. We theoretically show that the hard prototype is used in the contrastive loss to emphasize divergence. Additionally, instead of rigidly aligning query images to a specific prototype, we generate the dynamic prototype by randomly picking samples within a cluster. The dynamic prototype is used to encourage the variety. Finally, we introduce a progressive learning strategy to gradually shift the model's attention towards divergence and variety, avoiding cluster deterioration. Extensive experiments conducted on the publicly available SYSU-MM01 and RegDB datasets validate the effectiveness of the proposed method.