AI Paper Atlas

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

Adjustment and Alignment for Unbiased Open Set Domain Adaptation

Wuyang Li, Jie Liu, Bo Han, Yixuan Yuan

CVPR 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 62 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 FDA to debias source-domain learning (ablation)ANNA · Office-HomeHOS: 65.9 -> 68.2Improved
Add full DCA with base- and novel-class alignment (ablation)ANNA · Office-HomeHOS: 65.9 -> 69.0Improved
Add FDA together with both DCA alignment heads (ablation)ANNA · Office-HomeHOS: 65.9 -> 70.3Improved
Add base-class alignment head (ablation)ANNA DCA · Office-HomeOS*: 62.2 -> 63.7Improved
Add novel-class alignment head (ablation)ANNA DCA · Office-HomeUNK: 70.9% -> 76.0%Improved
Set FDA loss weight λ1 to 0.5 instead of 1.0 (ablation)ANNA · Office-HomeHOS: 70.7 -> 69.5Hurt
Set FDA loss weight λ1 to 2.0 instead of 1.0 (ablation)ANNA · Office-HomeHOS: 70.7% to 70.1%Hurt
Set FDA loss weight λ1 to 2.0 instead of 1.0 (ablation)ANNA · Image-CLEFHOS: 81.4% to 81.2%Hurt
Set DCA loss weight λ2 to 0.5 or 2.0 instead of 1.0 (ablation)ANNA · Office-HomeHOS: 70.7 -> 69.3; 70.7 -> 69.6Hurt
Set DCA loss weight λ2 to 0.5 instead of 1.0 (ablation)ANNA · Image-CLEFHOS: 81.4 -> 79.0Hurt
Set DCA loss weight λ2 to 2.0 instead of 1.0 (ablation)ANNA · Image-CLEFHOS: 81.4 -> 81.3Hurt
Increase the novel-region selection threshold K too far (ablation)ANNA FDA · Office-Home Ar→ClUNKHurt

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