AI RESEARCH

ALADIN:Attribute-Language Distillation Network for Person Re-Identification

arXiv CS.CV

ArXi:2603.21482v1 Announce Type: new Recent vision-language models such as CLIP provide strong cross-modal alignment, but current CLIP-guided ReID pipelines rely on global features and fixed prompts. This limits their ability to capture fine-grained attribute cues and adapt to diverse appearances. We propose ALADIN, an attribute-language distillation network that distills knowledge from a frozen CLIP teacher to a lightweight ReID student.