AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Multimodal Causality-Driven Representation Learning for Generalizable Medical Image Segmentation

Xusheng Liang, Lihua Zhou, Nianxin Li, Miao Xu, Ziyang Song, Dong Yi, Jinlin Wu, Jiawei Ma, Hongbin Liu, Zhen Lei, Jiebo Luo

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add MTRS and CDRL (full MCDRL) over CLIP baseline (ablation)MCDRL · 5-site endoscopic DG averagemDice (%): 69.37 -> 88.46Improved
add Multimodal Target Region Selection to CDRL (ablation)MCDRL · 5-site endoscopic DG averagemDice (%): 80.47 -> 88.46Improved
add Causal-Driven Representation Learning to MTRS (ablation)MCDRL · 5-site endoscopic DG averagemDice (%): 78.71 -> 88.46Improved
use MCDRL instead of BiomedCoOpCLIP ViT-L/14 · 5-site endoscopic DG averageDice (%): 79.4 -> 81.6Improved
use larger CLIP backbone (ResNet-50 to ViT-L/14)MCDRL · 5-site endoscopic DG averageDice (%): 78.6 -> 81.6Improved
increase confounder dictionary size from 3 to 12 (ablation)MCDRL on ViT-L/14 · 5-site averageDice (%): 76.7 -> 81.6Improved
increase confounder dictionary size from 12 to 15 (ablation)MCDRL on ViT-L/14 · 5-site averageDice (%): 81.6 -> 81.4No clear effect
increase causal network depth from 1 to 3 layers (ablation)MCDRL on ViT-L/14 · 5-site averageDice (%): 78.7 -> 81.6Improved
increase causal network depth from 3 to 5 layers (ablation)MCDRL on ViT-L/14 · 5-site averageDice (%): 81.6 -> 82.0No clear effect
use MCDRL instead of baseline on nodule lesionsCLIP backbone · lesion typesmDice (%): 73.5 -> 84.9Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy