AI Paper Atlas

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

ICCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-modality medical segmentation adaptation · 4 citations (OpenAlex)

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 changedWhereMeasuredEffect
add VLM-attribute learning to FairAP (ablation)FairAP · FairDomain Cup (Race)ES-Dice: 0.811 -> 0.828Improved
add VLM-attribute learning to FairAP (ablation)FairAP · FairDomain Rim (Race)ES-Dice: 0.694 -> 0.711Improved
add VLM-attribute learning to FairAP (ablation)FairAP · FairDomain Cup (Ethnicity)ES-Dice: 0.821 -> 0.836Improved
add VLM-attribute learning to FairAP (ablation)FairAP · FairDomain Rim (Ethnicity)ES-Dice: 0.781 -> 0.784Improved
add VLM-attribute learning to FairAP (ablation)FairAP · FairDomain Rim (Race)ES-IoU: 0.575 -> 0.592Improved
use attribute-only or polysemy-only selection instead of jointly (ablation)Fair-Attr / Fair-Poly · FairDomain (Race)Dice and IoUMixed
add both attribute and polysemy selection jointly (ablation)FairAP · FairDomain (Race)Dice and IoUImproved
increase labeling quota beyond 5% (ablation)FairAP · FairDomain (Race)ES-DiceNo clear effect
FairAP versus fairness-aware DA DAFormer-FIAFairAP · FairDomain Rim (Race)ES-IoU: 0.363 -> 0.592Improved
FairAP versus ADA method STDRFairAP · FairDomain Rim (Race)ES-Dice: 0.688 -> 0.711Improved
FairAP versus ADA method STDRFairAP · FairDomain Rim (Race)Dice: 0.781 -> 0.791Improved
DAFormer unsupervised adaptation on rim segmentationDAFormer · FairDomain Rim (Race)ES-IoU: 0.334 -> 0.199Hurt

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy