Research map / Label-efficient and robust learning / Domain adaptation and generalization
SDC-UDA: Volumetric Unsupervised Domain Adaptation Framework for Slice-Direction Continuous Cross-Modality Medical Image Segmentation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 SDC-UDA instead of PSIGAN | CrossMoDA (T1→T2) · CrossMoDA (T1→T2), mean | Dice: 47.3 -> 84.8 | Helped |
| Use SDC-UDA instead of PSIGAN | CrossMoDA (T1→T2) · CrossMoDA (T1→T2), mean | ASSD: 4.1 -> 0.33 | Helped |
| Use SDC-UDA instead of SIFA | MMWHS cardiac structures (MR→CT) · MMWHS cardiac structures (MR→CT), mean | Dice: 75.3 -> 85.5 | Helped |
| Use SDC-UDA instead of SIFA | MMWHS cardiac structures (MR→CT) · MMWHS cardiac structures (MR→CT), mean | ASSD: 5.5 -> 3.3 | Helped |
| Add intra/inter-slice attention to image translation (ablation) | SDC-UDA · CrossMoDA (T1→T2), VS and Cochlea | Dice: 71.5 -> 80.3 (VS); 72.7 -> 74.5 (C) | Helped |
| Add intra/inter-slice attention to image translation (ablation) | SDC-UDA · CrossMoDA (T1→T2), VS and Cochlea | ASSD: 5.91 -> 1.66 (VS); 1.83 -> 0.67 (C) | Helped |
| Add self-training without pseudo-label refinement (ablation) | SDC-UDA with intra/inter-slice attention · CrossMoDA (T1→T2), VS and Cochlea | Dice: 80.3 -> 83.2 (VS); 74.5 -> 76.7 (C) | Helped |
| Add self-training without pseudo-label refinement (ablation) | SDC-UDA with intra/inter-slice attention · CrossMoDA (T1→T2), VS and Cochlea | ASSD: 1.66 -> 0.58 (VS); 0.67 -> 0.79 (C) | Mixed |
| Add pseudo-label refinement to self-training (ablation) | SDC-UDA · CrossMoDA (T1→T2), VS and Cochlea | Dice: 83.2 -> 84.6 (VS); 76.7 -> 84.9 (C) | Helped |
| Add pseudo-label refinement to self-training (ablation) | SDC-UDA · CrossMoDA (T1→T2), VS and Cochlea | ASSD: 0.58 -> 0.51 (VS); 0.79 -> 0.14 (C) | Helped |
Closest papers by meaning
- MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling (CVPR 2024 · similarity 0.89)
- A Unified Degradation-Robust Approach to SSL and UDA for 3D Medical Images (AAAI 2025 · similarity 0.87)
- One-to-Multiple: A Progressive Style Transfer Unsupervised Domain-Adaptive Framework for Kidney Tumor Segmentation (NeurIPS 2024 · similarity 0.87)
- UniPro: Unified Multi-Mode Medical Image Segmentation from 2D Images to 3D Volumes via Propagation (NeurIPS 2026 · similarity 0.86)
- UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation (NeurIPS 2025 · similarity 0.85)
- Universal Domain Adaptation for Semantic Segmentation (CVPR 2025 · 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.