AI RESEARCH
DAIT: Distillation from Vision-Language Models to Lightweight Classifiers with Adaptive Intermediate Teacher Transfer
arXiv CS.CV
•
ArXi:2603.15166v1 Announce Type: new Large-scale Vision-Language Models (VLMs) encode rich multimodal semantics that are highly beneficial for fine-grained visual categorization (FGVC). However, their prohibitive computational cost hinders practical deployment in resource-constrained environments. Although knowledge distillation contributes to transferring VLMs capacity to lightweight classifiers, conventional distillation mechanisms, which directly transfer from a generic VLM to a compact student, often yield suboptimal results due to severe architectural misalignment and