AI Paper Atlas

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

Measure The Feature Universe: Topology-based Pseudo Labeling and Gravity Consistency for Source-Free Domain Adaptation

Jae Yun Lee, Hyeok Nam, Sung In Cho

CVPR 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation

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 universe-aware pseudo labeling to SHOT (ablation)SHOT · Office-Home (average)accuracy: 71.9 -> 72.5Improved
add gravity consistency to SHOT (ablation)SHOT · Office-Home (average)accuracy: 71.9 -> 73.0Improved
combine universe-aware pseudo labeling with gravity consistency (ablation)SHOT · Office-Home (average)accuracy: 71.9 -> 74.4Improved
add gravity consistency without information maximization loss (ablation)weighted CE · DomainNet-126 (average)accuracy: 68.6 -> 66.3Hurt
add gravity consistency together with information maximization loss (ablation)CE + IM · DomainNet-126 (average)accuracy: 68.9 -> 73.6Improved
add virtual features (lambda 0 to 20) (ablation)universe-aware pseudo labeling · Office-Home (average)accuracy: 73.8 -> 74.4Improved
increase virtual features from 20 to 30 (ablation)universe-aware pseudo labeling · Office-Home (average)accuracy: 74.4 -> 74.0Hurt
use sqrt schedule for quantile instead of fixed values (ablation)reliable area scheduling · DomainNet-126 (average)accuracy: 73.1 -> 73.6Improved
use sqrt schedule instead of linear schedule (ablation)reliable area scheduling · DomainNet-126 (average)accuracy: 73.3 -> 73.6Improved
add KL-based consistency regularization to SHOTSHOT · Office-Home A to Paccuracy: 78.8 -> 80.2Improved
replace KL consistency with gravity consistencySHOT · Office-Home A to Paccuracy: 80.2 -> 80.9Improved
add gravity consistency to existing SFDA methodsSHOT, GKD, TPDS · DomainNet-126 (average)accuracy: 68.1 -> 73.2 (SHOT)Improved

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