Cloth-aware Augmentation for Cloth-generalized Person Re-identification

Fangyi Liu, Mang Ye, Bo Du

Abstract: Person re-identification (ReID) is crucial in video surveillance, aiming to match individuals across different camera views while cloth-changing person re-identification (CC-ReID) focuses on pedestrians changing attire. Many existing CC-ReID methods overlook generalization, crucial for universality across cloth-consistent and cloth-changing scenarios. This paper pioneers exploring the cloth-generalized person re-identification (CG-ReID) task and introduces the Cloth-aware Augmentation (CaAug) strategy. Comprising domain augmentation and feature augmentation, CaAug aims to learn identity-relevant features adaptable to both scenarios. Domain augmentation involves creating diverse fictitious domains, simulating various clothing scenarios. Supervising features from different cloth domains enhances robustness and generalization against clothing changes. Additionally, for feature augmentation, element exchange introduces diversity concerning clothing changes. Regularizing the model with these augmented features strengthens resilience against clothing change uncertainty. Extensive experiments on cloth-changing datasets demonstrate the efficacy of our approach, consistently outperforming state-of-the-art methods. Our codes will be publicly released soon.

Primary Subject Area: [Experience] Multimedia Applications

Secondary Subject Area: [Content] Media Interpretation

Relevance To Conference: Person re-identification is a technique used in computer vision and multimedia processing to identify individuals across different cameras or modalities, even when they may be wearing different clothes. Traditional person re-identification algorithms rely heavily on facial features or body characteristics, which can be limited when individuals are occluded or wear different clothing. Cloth-generalized re-identification algorithms complement these techniques by focusing on clothing attributes, leading to more accurate identification.

Submission Number: 1961