Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains. (arXiv:2111.12853v3 [cs.CV] UPDATED)

Domain generalization (DG) is a difficult transfer learning problem aiming to
learn a generalizable model for unseen domains. Recent foundation models (FMs)
are robust to many distribution shifts and, therefore, should substantially
improve the performance of DG. In this work, we study generic ways to adopt
CLIP, a Visual-Language Foundation Model, for DG problems in image
classification. While ERM greatly improves the accuracy with bigger backbones
and training datasets using standard DG benchmarks, fine-tuning FMs is not
practical in many …

arxiv clip cv learning