Deeply Coupled Cross-Modal Prompt Learning
Xuejing Liu, Wei Tang, Jinghui Lu, Rui Zhao, Zhaojun Guo, Fei Tan
Abstract
Recent advancements in multimodal foundation models (e.g., CLIP) have excelled in zero-shot generalization. Prompt tuning involved in the knowledge transfer from foundation models to downstream tasks has gained significant attention recently. Existing prompt-tuning methods in cross-modal learning, however, either solely focus on language branch, or learn vision-language interaction in a shallow mechanism. In this context, we propose a Deeply coupled Cross-modal Prompt learning (DCP) method based on CLIP. DCP flexibly accommodates the interplay between vision and language with a Cross-Modal Prompt Attention (CMPA) mechanism, which enables the mutual exchange of respective representation through a well-connected multi-head attention progressively and strongly. We then conduct comprehensive few-shot learning experiments on 11 image classification datasets and analyze the robustness to domain shift as well. Thorough experimental analysis evidently demonstrates the superb few-shot generalization and compelling domain adaption capacity of a well-executed DCP.- Anthology ID:
- 2023.findings-acl.504
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7957–7970
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.504
- DOI:
- 10.18653/v1/2023.findings-acl.504
- Cite (ACL):
- Xuejing Liu, Wei Tang, Jinghui Lu, Rui Zhao, Zhaojun Guo, and Fei Tan. 2023. Deeply Coupled Cross-Modal Prompt Learning. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7957–7970, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Deeply Coupled Cross-Modal Prompt Learning (Liu et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2023.findings-acl.504.pdf