Research map / Label-efficient and robust learning / Domain adaptation and generalization
Unsupervised Domain Adaptation for Medical Image Segmentation by Selective Entropy Constraints and Adaptive Semantic Alignment
Wei Feng, Lie Ju, Lin Wang, Kaimin Song, Xin Zhao, Zongyuan Ge
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 |
|---|---|---|---|
| Use the full method instead of CRST | Cross-modality cardiac segmentation · Cardiac CT → Cardiac MRI | Average Dice: 5.1% | Improved |
| Use the full method instead of CRST | Cross-modality cardiac segmentation · Cardiac CT → Cardiac MRI | Average ASD: 1.3% | Improved |
| Use the full method instead of CRST | Cross-modality cardiac segmentation · Cardiac MRI → Cardiac CT | Average Dice: 5.4% | Improved |
| Use the full method instead of CRST | Cross-modality cardiac segmentation · Cardiac MRI → Cardiac CT | Average ASD: 1.4% | Improved |
| Add selective entropy constraints (ablation) | Adversarial-training cardiac segmentation model · Cardiac CT → Cardiac MRI | Average Dice: 61.9 -> 65.1 | Improved |
| Add adaptive semantic alignment (ablation) | Adversarial-training cardiac segmentation model · Cardiac CT → Cardiac MRI | Average Dice: 61.9 -> 64.5 | Improved |
| Apply entropy minimization to all pixels rather than selectively to reliable pixels and unreliable pixels (ablation) | Selective entropy constraints · Cardiac CT → Cardiac MRI | Average Dice: 69.9 -> 62.5 | Hurt |
| Add entropy maximization on unreliable pixels (ablation) | Selective entropy constraints · Cardiac CT → Cardiac MRI | Average Dice: 64.7 -> 69.9 | Improved |
| Remove unreliable pixels when calculating prototypes (ablation) | Adaptive semantic alignment · Cardiac CT → Cardiac MRI | Average Dice: 66.5 -> 69.9 | Improved |
Closest papers by meaning
- Reducing Domain Gap in Frequency and Spatial Domain for Cross-Modality Domain Adaptation on Medical Image Segmentation (AAAI 2023 · similarity 0.90)
- Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation (AAAI 2019 · similarity 0.90)
- Single-Domain Generalization in Medical Image Segmentation via Test-Time Adaptation from Shape Dictionary (AAAI 2022 · similarity 0.89)
- MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling (CVPR 2024 · similarity 0.87)
- S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical Imaging (AAAI 2025 · similarity 0.87)
- Learning Generalized Medical Image Segmentation from Decoupled Feature Queries (AAAI 2024 · similarity 0.87)
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.
