AI RESEARCH

Multi-Grained Vision-Language Alignment for Domain Generalized Person Re-Identification

arXiv CS.CV

ArXi:2603.14012v1 Announce Type: new Domain Generalized person Re-identification (DG Re-ID) is a challenging task, where models are trained on source domains but tested on unseen target domains. Although previous pure vision-based models have achieved significant progress, the performance remains further improved. Recently, Vision-Language Models (VLMs) present outstanding generalization capabilities in various visual applications. However, directly adapting a VLM to Re-ID shows limited generalization improvement.