PAND: Prompt-Aware Neighborhood Distillation for Lightweight Fine-Grained Visual Classification 事件

PAND: Prompt-Aware Neighborhood Distillation for Lightweight Fine-Grained Visual Classification arXiv:2602.07768v3 Announce Type: replace Abstract: Distilling knowledge from large Vision-Language Models (VLMs) into lightweight networks is crucial yet challenging in Fine-Grained Visual Classification (FGVC), due to the reliance on fixed prompts and global alignment. To address this, we propose PAND (Prompt-Aware Neighborhood Distillation), a two-stage framework that decouples semantic calibratio