AI Paper Atlas

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

Customizing Domain Adapters for Domain Generalization

Yuyang Ji, Zeyi Huang, Haohan Wang, Yong Jae Lee

ICCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 0 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 router loss (ablation)3 ViT adapters · PACSaccuracy (%): 88.0 -> 88.5Improved
add router loss (ablation)3 Conv adapters · PACSaccuracy (%): 88.3 -> 88.7Improved
add router loss (ablation)3 customized adapters · PACSaccuracy (%): 88.9 -> 89.4Improved
add router loss (ablation)5 customized adapters · DomainNetaccuracy (%): 49.6 -> 50.3Improved
combine ViT and Conv adapters (customized) instead of one adapter type (ablation)2 adapters · PACSaccuracy (%): 87.9 -> 88.9Improved
increase number of identical ViT adapters from 2 to 3 (ablation)ViT adapter · PACSaccuracy (%): 87.9 -> 88.0No clear effect
increase number of customized adapters from 2 to 3 without router loss (ablation)customized adapter · PACSaccuracy (%): 88.9 -> 88.9No clear effect
choose adapters with GPT-4 instead of empirical selection (ablation)CDA · PACSaccuracy (%): 89.4 -> 89.3No clear effect
add CDA architecture on top of ViT-S ERMViT-S/16 ERM · PACSaccuracy (%): 86.2 -> 89.4Improved
add CDA architecture on top of ViT-B ERMViT-B/16 ERM · PACSaccuracy (%): 88.8 -> 90.1Improved
add CDA to SWADSWAD · PACSaccuracy (%): 88.1 -> 90.3Improved
add CDA to W2DW2D · PACSaccuracy (%): 86.6 -> 89.9Improved

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