MaPLe: Multi-modal Prompt LearningShow others and affiliations
2023 (English)In: 2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), IEEE COMPUTER SOC , 2023, p. 19113-19122Conference paper, Published paper (Refereed)
Abstract [en]
Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to perform well. Inspired by the Natural Language Processing (NLP) literature, recent CLIP adaptation approaches learn prompts as the textual inputs to ne-tune CLIP for downstream tasks. We note that using prompting to adapt representations in a single branch of CLIP (language or vision) is sub-optimal since it does not allow the exibility to dynamically adjust both representation spaces on a downstream task. In this work, we propose Multi-modal Prompt Learning (MaPLe) for both vision and language branches to improve alignment between the vision and language representations. Our design promotes strong coupling between the vision-language prompts to ensure mutual synergy and discourages learning independent uni-modal solutions. Further, we learn separate prompts across different early stages to progressively model the stage-wise feature relationships to allow rich context learning. We evaluate the effectiveness of our approach on three representative tasks of generalization to novel classes, new target datasets and unseen domain shifts. Compared with the state-of-the-art method Co-CoOp, MaPLe exhibits favorable performance and achieves an absolute gain of 3.45% on novel classes and 2.72% on overall harmonic-mean, averaged over 11 diverse image recognition datasets. Our code and pre-trained models are available at https://github.com/muzairkhattak/multimodal-prompt-learning.
Place, publisher, year, edition, pages
IEEE COMPUTER SOC , 2023. p. 19113-19122
Series
IEEE Conference on Computer Vision and Pattern Recognition, ISSN 1063-6919, E-ISSN 2575-7075
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:liu:diva-199351DOI: 10.1109/CVPR52729.2023.01832ISI: 001062531303041ISBN: 9798350301298 (electronic)ISBN: 9798350301304 (print)OAI: oai:DiVA.org:liu-199351DiVA, id: diva2:1815359
Conference
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, CANADA, jun 17-24, 2023
2023-11-282023-11-282023-11-28