AI Paper Atlas

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

SelfReg: Self-Supervised Contrastive Regularization for Domain Generalization

Daehee Kim, Youngjun Yoo, Seunghyun Park, Jinkyu Kim, Jaekoo Lee

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Foundation-model domain generalization · 290 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 IDCL (ablation)SelfReg · PACSaccuracy: 83.30 -> 83.62Improved
add SWA (ablation)SelfReg · PACSaccuracy: 83.05 -> 83.30Improved
add CDPL (ablation)SelfReg · PACSaccuracy: 82.84 -> 83.05Improved
add two-domain mixup (ablation)SelfReg · PACSaccuracy: 82.75 -> 82.84Improved
add feature-level dissimilarity loss (ablation)SelfReg · PACSaccuracy: 82.62 -> 82.75Improved
add logit-level dissimilarity loss (ablation)baseline ERM · PACSaccuracy: 81.12 -> 82.62Improved
add SelfReg to ERMERM ResNet-18 · PACSaccuracy: 81.12 -> 83.62Improved
replace RSC with SelfRegResNet-18 · PACSaccuracy: 82.10 -> 83.62Improved
replace RSC with SelfRegsingle-source training · PACS single-sourceaccuracy: 58.66 -> 59.59Improved
add SelfReg to ERMResNet-50 DomainBed · DomainNetaccuracy: 40.9 -> 42.8Improved
add SelfReg to ERMResNet-50 DomainBed · OfficeHomeaccuracy: 66.5 -> 67.9Improved
add SelfReg to ERMResNet-50 DomainBed · DomainBed average over 7 datasetsaccuracy: 66.6 -> 67.3Improved

Later papers that compared with this method

4 later accepted papers report SelfReg as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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