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

2026-04-21

AI Summary

Current person re-identification methods rely heavily on large-scale annotated data and lack explicit modeling of identity-related causal cues, resulting in poor generalization across domains. This work proposes ReID-R, a novel reasoning-driven paradigm that integrates chain-of-thought (CoT) reasoning with reinforcement learning for the first time. Without requiring CoT annotations, ReID-R employs discriminative reasoning pre-warming and a non-trivial sampling strategy to guide the model toward identity-relevant features. Using only 14.3K training samples—approximately 20.9% of conventional dataset sizes—the method achieves state-of-the-art or comparable performance across multiple ReID benchmarks while offering an interpretable identity reasoning process.

Technology Category

• Knowledge Representation and Reasoning: Common-Sense Reasoning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Reasoning under Uncertainty: Causality

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

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.

Problem

• person re-identification
• identity-discriminative representations
• multi-scene generality
• reasoning
• representation robustness

Innovation

• reinforcement reasoning
• chain-of-thought
• person re-identification
• scene-generalizable
• identity-discriminative representation