AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Safe Generalization: Mitigating Catastrophic Forgetting in Single-Source Multi-Organ Segmentation via Collaborative Causal Learning

Yucheng Song, Ruoxi Yu, Feng Shu, Cheng Huang, HaoKang Ding, Zhifang Liao

ECCV 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization · 0 citations (OpenAlex)

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 Orthogonal Structure Disentanglement (OSD) (ablation)baseline U-Net · Abdominal CT->MRIDice: 55.98 -> 59.33Improved
add Anatomy-Guided Local Causal Intervention (AG-LCI) (ablation)baseline U-Net · Abdominal CT->MRIDice: 55.98 -> 60.76Improved
add Collaborative Learning constraint (CL) (ablation)baseline U-Net · Abdominal CT->MRIDice: 55.98 -> 70.59Improved
add CL to OSD (ablation)OSD variant · Abdominal CT->MRIDice: 59.33 -> 85.34Improved
add CL to AG-LCI (ablation)AG-LCI variant · Abdominal CT->MRIDice: 60.76 -> 79.12Improved
add AG-LCI to OSD+CL (full model) (ablation)CCL-Net · Abdominal CT->MRIDice: 85.34 -> 86.23Improved
add OSD to AG-LCI+CL (full model) (ablation)CCL-Net · Abdominal CT->MRIDice: 79.12 -> 86.23Improved
add CL module (ablation)CCL-Net · Average SFM over 4 source domainsSFM: 8.87 -> 1.96Improved
add CL module (ablation)CCL-Net · Cardiac bSSFP source SFMSFM: 10.45 -> 3.29Improved
use CCL-Net instead of ICMSegCCL-Net · Cardiac bSSFP->LGE MYODice: 80.02 -> 81.32Improved
use CCL-Net instead of CutoutCCL-Net · Abdominal MRI source SFMSFM: 14.90 -> 1.07Improved
use CCL-Net instead of ICMSegCCL-Net · Abdominal CT->MRIDice: 85.63 -> 86.23Improved

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