MCPL: Multi-Modal Collaborative Prompt Learning for Medical Vision-Language Model

计算机科学 情态动词 人工智能 医学影像学 计算机视觉 自然语言处理 化学 高分子化学
作者
Pengyu Wang,Huaqi Zhang,Yixuan Yuan
出处
期刊:IEEE Transactions on Medical Imaging [Institute of Electrical and Electronics Engineers]
卷期号:43 (12): 4224-4235 被引量:16
标识
DOI:10.1109/tmi.2024.3418408
摘要

Multi-modal prompt learning is a high-performance and cost-effective learning paradigm, which learns text as well as image prompts to tune pre-trained vision-language (V-L) models like CLIP for adapting multiple downstream tasks. However, recent methods typically treat text and image prompts as independent components without considering the dependency between prompts. Moreover, extending multi-modal prompt learning into the medical field poses challenges due to a significant gap between general- and medical-domain data. To this end, we propose a Multi-modal Collaborative Prompt Learning (MCPL) pipeline to tune a frozen V-L model for aligning medical text-image representations, thereby achieving medical downstream tasks. We first construct the anatomy-pathology (AP) prompt for multi-modal prompting jointly with text and image prompts. The AP prompt introduces instance-level anatomy and pathology information, thereby making a V-L model better comprehend medical reports and images. Next, we propose graph-guided prompt collaboration module (GPCM), which explicitly establishes multi-way couplings between the AP, text, and image prompts, enabling collaborative multi-modal prompt producing and updating for more effective prompting. Finally, we develop a novel prompt configuration scheme, which attaches the AP prompt to the query and key, and the text/image prompt to the value in self-attention layers for improving the interpretability of multi-modal prompts. Extensive experiments on numerous medical classification and object detection datasets show that the proposed pipeline achieves excellent effectiveness and generalization. Compared with state-of-the-art prompt learning methods, MCPL provides a more reliable multi-modal prompt paradigm for reducing tuning costs of V-L models on medical downstream tasks. Our code: https://github.com/CUHK-AIM-Group/MCPL.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
酷波er的应助被千里洛采纳,获得10
刚刚
1秒前
落羽发布了新的文献求助10
1秒前
1秒前
cc完成签到,获得积分0
2秒前
募雨qaq发布了新的文献求助10
2秒前
啦啦啦完成签到,获得积分20
2秒前
2秒前
3秒前
思源的应助被elysia采纳,获得30
3秒前
3秒前
3秒前
3秒前
oosr发布了新的文献求助10
4秒前
4秒前
pp发布了新的文献求助10
4秒前
IceyCNZ发布了新的文献求助10
4秒前
初(*^▽^*)心的应助被哭泣冬瓜采纳,获得10
5秒前
酷波er的应助被檀兮尔采纳,获得10
5秒前
Czz发布了新的文献求助10
5秒前
6秒前
serena发布了新的文献求助20
6秒前
忧心的曼凝的应助被沧海云帆采纳,获得10
6秒前
QQ完成签到,获得积分10
6秒前
6秒前
Brian发布了新的文献求助10
6秒前
nn完成签到,获得积分10
7秒前
科研通AI6.4的应助被Wd采纳,获得10
7秒前
石心粥发布了新的文献求助10
7秒前
8秒前
爆米花的应助被MRCHONG采纳,获得10
8秒前
小马同学发布了新的文献求助10
8秒前
搜集达人的应助被坚定的问芙采纳,获得10
9秒前
年轻雁枫完成签到,获得积分10
9秒前
sun发布了新的文献求助10
9秒前
俊逸博超完成签到,获得积分10
9秒前
hhhhh完成签到,获得积分10
9秒前
周周周发布了新的文献求助10
9秒前
哭泣冬瓜完成签到,获得积分10
10秒前
星辰大海的应助被繁荣的尔风采纳,获得10
10秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183792
求助须知:如何正确求助?哪些是违规求助? 9573020
关于积分的说明 21828776
捐赠科研通 7780959
什么是DOI,文献DOI怎么找? 3434116
关于科研通互助平台的介绍 2558301
邀请新用户注册赠送积分活动 2480611