pith. sign in

arxiv: 2408.16930 · v1 · pith:DYYBCIIYnew · submitted 2024-08-29 · 💻 cs.CV

VLM-KD: Knowledge Distillation from VLM for Long-Tail Visual Recognition

classification 💻 cs.CV
keywords knowledgemodeldistillationsupervisiontextvisuallong-tailnovel
0
0 comments X
read the original abstract

For visual recognition, knowledge distillation typically involves transferring knowledge from a large, well-trained teacher model to a smaller student model. In this paper, we introduce an effective method to distill knowledge from an off-the-shelf vision-language model (VLM), demonstrating that it provides novel supervision in addition to those from a conventional vision-only teacher model. Our key technical contribution is the development of a framework that generates novel text supervision and distills free-form text into a vision encoder. We showcase the effectiveness of our approach, termed VLM-KD, across various benchmark datasets, showing that it surpasses several state-of-the-art long-tail visual classifiers. To our knowledge, this work is the first to utilize knowledge distillation with text supervision generated by an off-the-shelf VLM and apply it to vanilla randomly initialized vision encoders.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.