AI Paper Atlas

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

Dual Masked Generative Adversarial Transformer for Unsupervised Domain Adaptation

Lei Zhu, Xinxing Xu, Jun Zhou, Qiegen Liu, Rick Siow Mong Goh, Yong Liu

ECCV 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 0 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 masked generative adversarial adaptation instead of FADA (ablation)source-supervised ViT-B · DomainNet clp<->infaccuracy: 50.5 -> 51.7Improved
add MGAA on top of masked target domain learning (ablation)MTDL · DomainNet clp<->infaccuracy: 54.2 -> 55.3Improved
reduce both information gap and distribution discrepancy instead of information gap only (ablation)MTDL + MGAA · DomainNet clp<->infaccuracy: 54.7 -> 55.3Improved
use [CLS] token feature reconstruction instead of pixel reconstruction (ablation)MGAA · DomainNet clp<->infaccuracy: 47.6 -> 51.7Improved
use adversarial loss instead of l2 reconstruction loss (ablation)MGAA · DomainNet clp<->infaccuracy: 49.7 -> 51.7Improved
pixel reconstruction with l2 loss added to source training (ablation)source-supervised ViT-B · DomainNet clp<->infaccuracy: 45.4 -> 44.1Hurt
add masked source to target adversarial adaptation branch (dual) (ablation)Dual-MGAT · DomainNet clp<->infaccuracy: 51.7 -> 52.9; 55.3 -> 56.0Improved
Dual-MGAT vs PMTransDual-MGAT · DomainNet (30 tasks)accuracy: 52.4 -> 58.2Improved
Dual-MGAT vs MIC(SDAT)Dual-MGAT · Office-Homeaccuracy: 86.2 -> 89.1Improved
Dual-MGAT vs PMTrans on cataract domain shiftDual-MGAT · Cataract Slit-Lamp to CameraAUC: 85.9 -> 94.8Improved

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