AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification

Yu Tian, Congcong Wen, Min Shi, Muhammad Muneeb Afzal, Hao Huang, Muhammad Osama Khan, Yan Luo, Yi Fang, Mengyu Wang

ECCV 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-modality medical segmentation adaptation · 29 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
apply domain shift from EnFace to SLO fundus (no adaptation)TransUNet baseline · FairDomain-Segmentation, rim, genderES-Dice: 0.854 -> 0.485Hurt
add fair identity attention to DAFormer for domain adaptation (cup)DAFormer · FairDomain-Segmentation, cup, genderES-Dice: 0.781 -> 0.802Improved
add fair identity attention to DAFormer for domain adaptation (rim)DAFormer · FairDomain-Segmentation, rim, genderES-Dice: 0.344 -> 0.528Improved
add fair identity attention to DAFormer, compared with CBST on rim DADAFormer-FIA · FairDomain-Segmentation, rim, gender, DAES-Dice: CBST 0.693 vs DAFormer-FIA 0.528Hurt
add fair identity attention to DAFormer for domain generalizationDAFormer · FairDomain-Segmentation, cup, ethnicityES-Dice: 0.746 -> 0.785Improved
add fair identity attention to CDTrans for domain adaptation classificationCDTrans · FairDomain-Classification, genderES-AUC: 0.631 -> 0.633Improved
add fair identity attention to IRM for domain generalizationIRM · FairDomain-Classification, raceAUC overall: 0.672 -> 0.696Improved
add fair identity attention to IRM, Hispanic groupIRM · FairDomain-Classification, ethnicity, Hispanic groupAUC: 0.558 -> 0.580Improved
add FIA module to IRMIRM · computational costtraining time per epoch (s): 149 -> 157Hurt

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