Research map / Label-efficient and robust learning / Domain adaptation and generalization
Toward Fair and Accurate Cross-Domain Medical Image Segmentation: A VLM-Driven Active Domain Adaptation Paradigm
Hongqiu Wang, Wu Chen, Xiangde Luo, Zhaohu Xing, Lihao Liu, Jing Qin, Shaozhi Wu, Lei Zhu
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 VLM-attribute learning to FairAP (ablation) | FairAP · FairDomain Cup (Race) | ES-Dice: 0.811 -> 0.828 | Improved |
| add VLM-attribute learning to FairAP (ablation) | FairAP · FairDomain Rim (Race) | ES-Dice: 0.694 -> 0.711 | Improved |
| add VLM-attribute learning to FairAP (ablation) | FairAP · FairDomain Cup (Ethnicity) | ES-Dice: 0.821 -> 0.836 | Improved |
| add VLM-attribute learning to FairAP (ablation) | FairAP · FairDomain Rim (Ethnicity) | ES-Dice: 0.781 -> 0.784 | Improved |
| add VLM-attribute learning to FairAP (ablation) | FairAP · FairDomain Rim (Race) | ES-IoU: 0.575 -> 0.592 | Improved |
| use attribute-only or polysemy-only selection instead of jointly (ablation) | Fair-Attr / Fair-Poly · FairDomain (Race) | Dice and IoU | Mixed |
| add both attribute and polysemy selection jointly (ablation) | FairAP · FairDomain (Race) | Dice and IoU | Improved |
| increase labeling quota beyond 5% (ablation) | FairAP · FairDomain (Race) | ES-Dice | No clear effect |
| FairAP versus fairness-aware DA DAFormer-FIA | FairAP · FairDomain Rim (Race) | ES-IoU: 0.363 -> 0.592 | Improved |
| FairAP versus ADA method STDR | FairAP · FairDomain Rim (Race) | ES-Dice: 0.688 -> 0.711 | Improved |
| FairAP versus ADA method STDR | FairAP · FairDomain Rim (Race) | Dice: 0.781 -> 0.791 | Improved |
| DAFormer unsupervised adaptation on rim segmentation | DAFormer · FairDomain Rim (Race) | ES-IoU: 0.334 -> 0.199 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DAFormer — DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation (CVPR 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- FairCLIP: Harnessing Fairness in Vision-Language Learning (CVPR 2024 · similarity 0.88)
- FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scaling (ICLR 2024 · similarity 0.88)
- A Unified Degradation-Robust Approach to SSL and UDA for 3D Medical Images (AAAI 2025 · similarity 0.87)
- The Boundaries of Fair AI in Medical Image Prognosis: A Causal Perspective (NeurIPS 2025 · similarity 0.87)
- FairMedFM: Fairness Benchmarking for Medical Imaging Foundation Models (NeurIPS 2024 · similarity 0.87)
- S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical Imaging (AAAI 2025 · 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.
