Thinking Before Matching: A Reinforcement Reasoning Paradigm Towards General Person Re-Identification

TL;DR

This paper introduces ReID-R, a reasoning-driven paradigm for person re-identification that enhances identity understanding and generalization through a two-stage reinforcement reasoning approach, achieving competitive results with less data.

Contribution

ReID-R is a novel reasoning-based framework that explicitly incorporates chain-of-thought reasoning and reinforcement learning to improve person re-identification performance and interpretability.

Findings

ReID-R achieves competitive accuracy with only 14.3K data points.

The method outperforms some existing approaches on multiple benchmarks.

ReID-R provides high-quality interpretability of its reasoning process.

Abstract

Learning identity-discriminative representations with multi-scene generality has become a critical objective in person re-identification (ReID). However, mainstream perception-driven paradigms tend to identify fitting from massive annotated data rather than identity-causal cues understanding, which presents a fragile representation against multiple disruptions. In this work, ReID-R is proposed as a novel reasoning-driven paradigm that achieves explicit identity understanding and reasoning by incorporating chain-of-thought into the ReID pipeline. Specifically, ReID-R consists of a two-stage contribution: (i) Discriminative reasoning warm-up, where a model is trained in a CoT label-free manner to acquire identity-aware feature understanding; and (ii) Efficient reinforcement learning, which proposes a non-trivial sampling to construct scene-generalizable data. On this basis, ReID-R leverages high-quality reward signals to guide the model toward focusing on ID-related cues, achieving accurate reasoning and correct responses. Extensive experiments on multiple ReID benchmarks demonstrate that ReID-R achieves competitive identity discrimination as superior methods using only 14.3K non-trivial data (20.9% of the existing data scale). Furthermore, benefit from inherent reasoning, ReID-R can provide high-quality interpretation for results.