AI Paper Atlas

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

Re-Energizing Domain Discriminator With Sample Relabeling for Adversarial Domain Adaptation

Xin Jin, Cuiling Lan, Wenjun Zeng, Zhibo Chen

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 19 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 dynamic relabeling of well-aligned target samples (no mixup) (ablation)DANN · VisDA-2017accuracy: 61.23 -> 65.91Improved
add dynamic relabeling of well-aligned target samples (no mixup) (ablation)CDAN · VisDA-2017accuracy: 70.82 -> 75.62Improved
add dynamic relabeling (no mixup) (ablation)DANN · Office-31accuracy: 83.42 -> 85.24Improved
add dynamic relabeling (no mixup) (ablation)CDAN · Office-31accuracy: 87.90 -> 89.58Improved
add mixup within the updated source set (ablation)DANN+RADA · Office-31accuracy: 85.24 -> 86.79Improved
add mixup within the updated source set (ablation)CDAN+RADA · VisDA-2017accuracy: 75.62 -> 76.28Improved
add mixup within the updated source set (ablation)CDAN+RADA · Office-Homeaccuracy: 70.25 -> 71.37Improved
replace entropy re-weighting variants by RADA relabelingDANN · Digit-Five multi-sourceaccuracy: 86.1 -> 91.5Improved
vary threshold tau (ablation)DANN/CDAN+RADA w/o MU · VisDA-2017accuracyNo clear effect
vary patience K (ablation)DANN/CDAN+RADA w/o MU · VisDA-2017accuracyNo clear effect
add RADA to CDANCDAN · Digit-Five multi-sourceaccuracy: 88.7 -> 93.2Improved
add RADA to CDANCDAN · DomainNetaccuracy: 45.2 -> 47.5Improved

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