PAND: Prompt-Aware Neighborhood Distillation for Lightweight Fine-Grained Visual Classification
This addresses the problem of efficient fine-grained visual classification for resource-constrained applications, though it appears incremental as it builds on existing distillation methods.
The paper tackles the challenge of distilling knowledge from large vision-language models into lightweight networks for fine-grained visual classification by proposing PAND, a two-stage framework that decouples semantic calibration from structural transfer. The result shows that PAND consistently outperforms state-of-the-art methods on four benchmarks, with a ResNet-18 student achieving 76.09% accuracy on CUB-200, surpassing the baseline by 3.4%.
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 calibration from structural transfer. First, we incorporate Prompt-Aware Semantic Calibration to generate adaptive semantic anchors. Second, we introduce a neighborhood-aware structural distillation strategy to constrain the student's local decision structure. PAND consistently outperforms state-of-the-art methods on four FGVC benchmarks. Notably, our ResNet-18 student achieves 76.09% accuracy on CUB-200, surpassing the strong baseline VL2Lite by 3.4%. Code is available at https://github.com/LLLVTA/PAND.