Research map / Label-efficient and robust learning / Domain adaptation and generalization
What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentation
Check 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 the proposed transferable semantic transfer model instead of PyCDA | Endoscopic lesions segmentation · Endoscopic lesions test | mIoU: 63.70 -> 64.58 | Helped |
| Use the proposed transferable semantic transfer model instead of BDL | GTA → Cityscapes · GTA → Cityscapes | mIoU: 48.5 -> 49.2 | Helped |
| Use the proposed transferable semantic transfer model instead of PyCDA | SYNTHIA → Cityscapes · SYNTHIA → Cityscapes | mIoU: 46.7 -> 47.2 | Helped |
| Add quantified transferability (QT) (ablation) | Ours · Endoscopic lesions test | mIoU: 61.47 -> 64.58; -3.11 | Helped |
| Add pseudo labels (PL) (ablation) | Ours · Endoscopic lesions test | mIoU: 61.35 -> 64.58; -3.23 | Helped |
| Add transferability-aware bottleneck (TKB) (ablation) | Ours · Endoscopic lesions test | mIoU: 62.73 -> 64.58; -1.85 | Helped |
| Add attention on attention (AA) (ablation) | Ours · Endoscopic lesions test | mIoU: 63.06 -> 64.58; -1.52 | Helped |
| Add quantified transferability (QT) (ablation) | Ours · GTA → Cityscapes | mIoU: 45.7 -> 49.2 | Helped |
| Add pseudo labels (PL) (ablation) | Ours · GTA → Cityscapes | mIoU: 46.4 -> 49.2 | Helped |
| Add transferability-aware bottleneck (TKB) (ablation) | Ours · GTA → Cityscapes | mIoU: 47.5 -> 49.2 | Helped |
| Add attention on attention (AA) (ablation) | Ours · GTA → Cityscapes | mIoU: 48.0 -> 49.2 | Helped |
| Add quantified transferability (QT) (ablation) | Ours · SYNTHIA → Cityscapes | mIoU: 44.2 -> 47.2 | Helped |
Closest papers by meaning
- Knowledge Transfer Scaling Laws for 3D Medical Imaging (NeurIPS 2026 · similarity 0.86)
- One-to-Multiple: A Progressive Style Transfer Unsupervised Domain-Adaptive Framework for Kidney Tumor Segmentation (NeurIPS 2024 · similarity 0.86)
- Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentation (CVPR 2024 · similarity 0.85)
- Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading (NeurIPS 2024 · similarity 0.85)
- Unleashing the Potential of Vision-Language Pre-Training for 3D Zero-Shot Lesion Segmentation via Mask-Attribute Alignment (ICLR 2025 · similarity 0.85)
- S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical Imaging (AAAI 2025 · similarity 0.84)
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.