Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification

arXiv:2310.08255v2 Announce Type: replace
Abstract: Vision-Language Models (VLMs) such as CLIP are trained on large amounts of image-text pairs, resulting in remarkable generalization across several data distributions. However, in several cases, their expensive training and data collection/curation costs do not justify the end application. This motivates a vendor-client paradigm, where a vendor trains a large-scale VLM and grants only input-output access to clients on a pay-per-query basis in a black-box setting. The client aims to minimize inference cost by distilling …

abstract application arxiv cases classification client clip collection costs cs.cv curation data data collection domain however image language language models paradigm text the end training type vendor vision vision-language models vlms