Abstract | ||
---|---|---|
CLIP has shown a remarkable zero-shot capability on a wide range of vision tasks. Previously, CLIP is only regarded as a powerful visual encoder. However, after being pre-trained by language supervision from a large amount of image-caption pairs, CLIP itself should also have acquired some few-shot abilities for vision-language tasks. In this work, we empirically show that CLIP can be a strong vision-language few-shot learner by leveraging the power of language. We first evaluate CLIP's zero-shot performance on a typical visual question answering task and demonstrate a zero-shot cross-modality transfer capability of CLIP on the visual entailment task. Then we propose a parameter-efficient fine-tuning strategy to boost the few-shot performance on the vqa task. We achieve competitive zero/few-shot results on the visual question answering and visual entailment tasks without introducing any additional pre-training procedure. |
Year | DOI | Venue |
---|---|---|
2022 | 10.18653/v1/2022.acl-long.421 | PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), VOL 1: (LONG PAPERS) |
DocType | Volume | Citations |
Conference | Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Haoyu Song | 1 | 4 | 1.77 |
Li Dong | 2 | 582 | 31.86 |
Weinan Zhang | 3 | 46 | 11.98 |
Ting Liu | 4 | 2735 | 232.31 |
Furu Wei | 5 | 1956 | 107.57 |