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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add Orthogonal Structure Disentanglement (OSD) (ablation) | baseline U-Net · Abdominal CT->MRI | Dice: 55.98 -> 59.33 | Improved |
| add Anatomy-Guided Local Causal Intervention (AG-LCI) (ablation) | baseline U-Net · Abdominal CT->MRI | Dice: 55.98 -> 60.76 | Improved |
| add Collaborative Learning constraint (CL) (ablation) | baseline U-Net · Abdominal CT->MRI | Dice: 55.98 -> 70.59 | Improved |
| add CL to OSD (ablation) | OSD variant · Abdominal CT->MRI | Dice: 59.33 -> 85.34 | Improved |
| add CL to AG-LCI (ablation) | AG-LCI variant · Abdominal CT->MRI | Dice: 60.76 -> 79.12 | Improved |
| add AG-LCI to OSD+CL (full model) (ablation) | CCL-Net · Abdominal CT->MRI | Dice: 85.34 -> 86.23 | Improved |
| add OSD to AG-LCI+CL (full model) (ablation) | CCL-Net · Abdominal CT->MRI | Dice: 79.12 -> 86.23 | Improved |
| add CL module (ablation) | CCL-Net · Average SFM over 4 source domains | SFM: 8.87 -> 1.96 | Improved |
| add CL module (ablation) | CCL-Net · Cardiac bSSFP source SFM | SFM: 10.45 -> 3.29 | Improved |
| use CCL-Net instead of ICMSeg | CCL-Net · Cardiac bSSFP->LGE MYO | Dice: 80.02 -> 81.32 | Improved |
| use CCL-Net instead of Cutout | CCL-Net · Abdominal MRI source SFM | SFM: 14.90 -> 1.07 | Improved |
| use CCL-Net instead of ICMSeg | CCL-Net · Abdominal CT->MRI | Dice: 85.63 -> 86.23 | Improved |
Closest papers by meaning
- Perturbating, Tuning, and Collaborating: Harnessing Vision Foundation Models for Single Domain Generalization on Medical Imaging (AAAI 2025 · similarity 0.88)
- Why Invariance is Not Enough for Biomedical Domain Generalization and How to Fix It (NeurIPS 2026 · similarity 0.87)
- FR²Seg: Continual Segmentation Across Multiple Sites via Fourier Style Replay and Adaptive Consistency Regularization (AAAI 2025 · similarity 0.85)
- TinyMIG: Transferring Generalization from Vision Foundation Models to Single-Domain Medical Imaging (ICML 2025 · similarity 0.85)
- Domain Generalized Medical Landmark Detection via Robust Boundary-Aware Pre-Training (AAAI 2025 · similarity 0.85)
- Knowledge Transfer Scaling Laws for 3D Medical Imaging (NeurIPS 2026 · similarity 0.85)
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.
