AI Paper Atlas

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

Contrastive Vicinal Space for Unsupervised Domain Adaptation

Jaemin Na, Dongyoon Han, Hyung Jin Chang, Wonjun Hwang

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 24 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 EMP-Mixup (ablation)MSTN baseline · Office-31 (avg)accuracy: 86.5 -> 90.4Improved
add contrastive loss on top of EMP-Mixup (ablation)MSTN + EMP-Mixup · Office-31 (avg)accuracy: 90.4 -> 91.1Improved
add label-consensus loss on top of EMP-Mixup and contrastive loss (ablation)MSTN + EMP-Mixup + contrastive loss · Office-31 (avg)accuracy: 91.1 -> 91.8Improved
add contrastive loss (ablation)MSTN + EMP-Mixup · Office-31 A->Daccuracy: 95.6 -> 97.2Improved
add contrastive loss (ablation)MSTN + EMP-Mixup · Office-31 A->Waccuracy: 95.9 -> 97.1Improved
add label-consensus loss (ablation)MSTN + EMP-Mixup + contrastive loss · Office-31 W->Aaccuracy: 76.4 -> 78.4Improved
add label-consensus loss (ablation)MSTN + EMP-Mixup + contrastive loss · Office-31 D->Aaccuracy: 76.4 -> 77.5Improved
add EMP-Mixup (ablation)DANN baseline · Office-31 (avg)accuracy: 82.2 -> 89.8Improved
add contrastive loss (ablation)DANN + EMP-Mixup · Office-31 (avg)accuracy: 89.8 -> 90.2Improved
add label-consensus loss (ablation)DANN + EMP-Mixup + contrastive loss · Office-31 (avg)accuracy: 90.2 -> 91.0Improved
apply CoVi instead of MSTN baselineMSTN · VisDA-Caccuracy: 65.0 -> 88.5Improved
apply CoVi instead of MSTN baselineMSTN · PACS (multi-source)accuracy: 86.95 -> 93.52Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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