Rethinking Clothes Changing Person ReID: Conflicts, Synthesis, and Optimization

TL;DR

This paper addresses the challenge of clothes-changing person re-identification by analyzing conflicts between standard and clothes-changing objectives, proposing synthetic data augmentation, and formulating a multi-objective optimization approach to improve performance.

Contribution

It introduces a Clothes-Changing Diffusion model for synthetic data generation and a multi-objective optimization framework to balance conflicting learning objectives in CC-ReID.

Findings

Synthetic clothes-varying images improve CC-ReID accuracy.

Decoupling objectives enhances performance under both protocols.

Multi-objective optimization outperforms single-task training.

Abstract

Clothes-changing person re-identification (CC-ReID) aims to retrieve images of the same person wearing different outfits. Mainstream researches focus on designing advanced model structures and strategies to capture identity information independent of clothing. However, the same-clothes discrimination as the standard ReID learning objective in CC-ReID is persistently ignored in previous researches. In this study, we dive into the relationship between standard and clothes-changing~(CC) learning objectives, and bring the inner conflicts between these two objectives to the fore. We try to magnify the proportion of CC training pairs by supplementing high-fidelity clothes-varying synthesis, produced by our proposed Clothes-Changing Diffusion model. By incorporating the synthetic images into CC-ReID model training, we observe a significant improvement under CC protocol. However, such improvement sacrifices the performance under the standard protocol, caused by the inner conflict between standard and CC. For conflict mitigation, we decouple these objectives and re-formulate CC-ReID learning as a multi-objective optimization (MOO) problem. By effectively regularizing the gradient curvature across multiple objectives and introducing preference restrictions, our MOO solution surpasses the single-task training paradigm. Our framework is model-agnostic, and demonstrates superior performance under both CC and standard ReID protocols.