CLIP Models are Few-Shot Learners: Empirical Studies on VQA and Visual Entailment

Haoyu Song, Li Dong, Weinan Zhang, Ting Liu, Furu Wei

BibTeX
@inproceedings{song2022clip,
  author = {Haoyu Song and Li Dong and Weinan Zhang and Ting Liu and Furu Wei},
  title = {{CLIP Models are Few-Shot Learners: Empirical Studies on VQA and Visual Entailment}},
  booktitle = {Annual Meeting of the Association for Computational Linguistics},
  year = {2022},
  doi = {10.18653/v1/2022.acl-long.421},
}
Figure