Iterative Self-Correction for Text-Driven Person Re-Identification with Large Vision-Language Models
Year: 2026
Type: conference-paper
Abstract: Person Re-Identification (ReID) has long struggled with the semantic gap between low-level visual features and high-level identity concepts.While Vision-Language Models (VLMs) offer promising semantic understanding, existing methods typically adopt a static "one-pass" paradigm, converting images to text once for retrieval.This approach suffers from two critical flaws: Information Bottleneck, where converting rich visuals into text causes detail loss, and Open-Loop Failure, where initial hallucinations propagate without recourse.To address this, we propose Auto-ReID, a novel framework that reformulates ReID as an iterative "Think-and-Refine" process.We first introduce a Hierarchical Progressive Tuning strategy to transform a generic VLM into a specialized Re-ID expert.During inference, we deploy a closed-loop architecture comprising a Reasoner for structured attribute extraction, a Hybrid Retriever that anchors dynamic semantic queries with stable visual features to prevent drift, and a Corrector that deconstructs and verifies candidates to iteratively optimize the search.Extensive experiments on ReID datasets demonstrate that our method significantly outperforms state-of-theart approaches, particularly in complex occlusion scenarios.Code can be found at
Institutions: Zhejiang University, National University of Singapore
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Award: G1101031052
OpenAlex ID: W7166853323