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
Bibkey:
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)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.findings-acl.504.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-5/2023.findings-acl.504.mp4