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.- Anthology ID:
- 2022.acl-long.421
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6088–6100
- Language:
- URL:
- https://aclanthology.org/2022.acl-long.421
- DOI:
- 10.18653/v1/2022.acl-long.421
- Cite (ACL):
- Haoyu Song, Li Dong, Weinan Zhang, Ting Liu, and Furu Wei. 2022. CLIP Models are Few-Shot Learners: Empirical Studies on VQA and Visual Entailment. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6088–6100, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- CLIP Models are Few-Shot Learners: Empirical Studies on VQA and Visual Entailment (Song et al., ACL 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.acl-long.421.pdf
- Data
- SNLI-VE, Visual Question Answering