Attribute-aware prompt learning for cloth-changing person re-identification

Abstract

Clothes-changing person re-identification (CC-ReID) is a challenging task with great practical value. Existing methods attempt to decouple clothes-independent features from the RGB modality alone and suffer from spatial redundancy. In this paper, we propose a novel Attribute-aware Prompt Learning (APL) framework for CC-ReID that comprises a frequency-aware visual prompt generator (FVPG) and a set of attribute-aware text prompts (ATP). Specifically, FVPG computes high-frequency components of images to provide additional body-shape information at low computational cost. ATP employs a CLIP model to learn clothes-independent features with the designed attribute-aware text prompts via vision-language contrastive learning. With a proposed two-stage training strategy, the APL framework can capture clothes-independent features, effectively improving the performance of CC-ReID. Extensive experiments demonstrate that the proposed APL can achieve state-of-the-art performance on three widely used clothes-changing person ReID benchmarks.