Silhouette-Driven Contrastive Learning for Unsupervised Person Re-Identification with Clothes Change
The core message of this paper is to propose a novel silhouette-driven contrastive learning framework, termed SiCL, for unsupervised long-term person re-identification with clothes change. SiCL incorporates both person silhouette information and hierarchical neighbor structure into a contrastive learning framework to guide the model for learning cross-clothes invariance features.