Research map / Detection and segmentation / Open-set and few-shot detection
Make Foundation Models Trustworthy Again: Causal Fine-Adaptation for Medical Image Segmentation
Hongpeng Yang, Yingxin Chen, Shiqiang Ma, Fei Guo
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 PCRU (MoCE + Causal Corrector) (ablation) | CausalBridgeNet (SAM2) · BraTS2025 Pre+Post TC | DSC: 80.93 -> 82.72 | Improved |
| add PCRU (ablation) | CausalBridgeNet (SAM2) · BraTS2025 Pre+Post RC | DSC: 80.26 -> 82.12 | Improved |
| add PCRU (ablation) | CausalBridgeNet (SAM2) · BraTS2025 Pre+Post RC | HD95: 7.32 -> 6.49 | Improved |
| add PCRU (ablation) | CausalBridgeNet (SAM2) · BraTS2025 Pre+Post WT | DSC: 90.74 -> 91.37 | Improved |
| add PCRU (ablation) | CausalBridgeNet (SAM2) · BraTS2025 Pre+Post WT | HD95: 4.98 -> 3.90 | Improved |
| add PCRU to U-KAN | U-KAN · BUSI | IoU: 63.38 -> 68.85 | Improved |
| add PCRU to U-KAN | U-KAN · BUSI | F1: 76.40 -> 80.86 | Improved |
| use frozen SAM2 backbone with causal correction instead of SegMamba | CausalBridgeNet (SAM2) · BraTS2025 Pre+Post TC | DSC: 78.20 -> 82.72 | Improved |
| use frozen SAM2 backbone with causal correction instead of SegMamba | CausalBridgeNet (SAM2) · BraTS2025 Pre+Post RC | DSC: 76.16 -> 82.12 | Improved |
| use SAM2 instead of CLIP as frozen backbone | CausalBridgeNet · BraTS2025 Pre-only avg | DSC: 91.01 -> 91.16 | No clear effect |
| use CausalBridgeNet (SAM2) instead of SegMamba | CausalBridgeNet · BraTS2025 Pre-only ET | HD95: 4.53 -> 3.82 | Improved |
| use CausalBridgeNet (SAM2) instead of SegResNet | CausalBridgeNet · BraTS2025 Pre-only avg | DSC: 90.29 -> 91.16 | Improved |
Closest papers by meaning
- Steady Progress Beats Stagnation: Mutual Aid of Foundation and Conventional Models in Mixed Domain Semi-Supervised Medical Image Segmentation (CVPR 2025 · similarity 0.88)
- S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical Imaging (AAAI 2025 · similarity 0.87)
- Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation (CVPR 2024 · similarity 0.86)
- GapMatch: Bridging Instance and Model Perturbations for Enhanced Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.86)
- Multi-view Evidential Learning-based Medical Image Segmentation (AAAI 2025 · similarity 0.86)
- Uncertainty-aware Fine-tuning of Segmentation Foundation Models (NeurIPS 2024 · similarity 0.86)
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.
