Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Quan, Wu, Jingze, Wang, Jialong, Xie, Xiaohua, Lai, Jianhuang, Chen, Hongbo
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.19218
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910153198010368
author Zhang, Quan
Wu, Jingze
Wang, Jialong
Xie, Xiaohua
Lai, Jianhuang
Chen, Hongbo
author_facet Zhang, Quan
Wu, Jingze
Wang, Jialong
Xie, Xiaohua
Lai, Jianhuang
Chen, Hongbo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_19218
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Thinking Before Matching: A Reinforcement Reasoning Paradigm Towards General Person Re-Identification
Zhang, Quan
Wu, Jingze
Wang, Jialong
Xie, Xiaohua
Lai, Jianhuang
Chen, Hongbo
Computer Vision and Pattern Recognition
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.
title Thinking Before Matching: A Reinforcement Reasoning Paradigm Towards General Person Re-Identification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.19218