AI Paper Atlas

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

Exploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptation

Yifan Wang, Lin Zhang, Ran Song, Hongliang Li, Paul L. Rosin, Wei Zhang

IJCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 9 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 source-domain loss L_s (ablation)full method · Office-31 UniDAH-score: 36.4 -> 88.7Improved
add unknown-affinity loss L_unk (ablation)full method · Office-31 UniDAH-score: 82.6 -> 88.7Improved
add uncertainty loss L_unc (ablation)full method · Office-31 UniDAH-score: 86.3 -> 88.7Improved
add known-affinity loss L_k (ablation)full method · Office-31 UniDAH-score: 86.5 -> 88.7Improved
increase neighbors k from 10 to 90 (ablation)full method · Office-31 W2DH-score: 98.3 -> 92.8Hurt
increase neighbors k from 10 to 90 (ablation)full method · Office-31 A2DH-score: 87.4 -> 84.0Hurt
scale threshold c_tau from 0.1 to 0.8 (ablation)full method · Office-31 UniDAH-score: 87.9 -> 88.4No clear effect
vary lambda weight on target losses (ablation)full method · Office-31 UniDAH-scoreNo clear effect
swap method to ours vs OVANet on new Art samplesOurs vs OVANet · Office-31 to OfficeHome ArtH-score: 88.2 -> 96.9Improved
swap method to ours vs OVANet on VGGNetOurs vs OVANet · Office-31 ODA (VGGNet)H-score: 88.7 -> 90.6Improved
use proposed method vs OVANet on OfficeHomeOurs vs OVANet · OfficeHome UniDAH-score: 71.8 -> 74.6Improved

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