AI Paper Atlas

Research map / Continual learning / Domain and prompt-based

On Generalizing Beyond Domains in Cross-Domain Continual Learning

Christian Simon, Masoud Faraki, Yi-Hsuan Tsai, Xiang Yu, Samuel Schulter, Yumin Suh, Mehrtash Harandi, Manmohan Chandraker

CVPR 2022 · Continual learning › Domain and prompt-based · approach: Domain-incremental learning with memory · 37 citations (OpenAlex)

Check 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
Use class-specific Mahalanobis metrics and biases in place of a standard classifierCross-domain continual learning · DomainNet and OfficeHome, unseen domainsaccuracyImproved
Add EMA-based distillation to MSL (ablation)MSL · DomainNet-Sketch, 10-taskaccuracy (%): 54.1 -> 56.4Improved
Add EMA-based distillation to MSL (ablation)MSL · PACS and NICO-Animalaccuracy: 2.1%Improved
Use EMA-based model updates for distillation rather than standard knowledge distillation (ablation)MSL · OfficeHome, 10-taskaccuracy: 2%Improved
Use EMA-based distillation (ablation)MSL · DomainNet, 10-taskbackward transfer rate: 10.1% vs 12.8%Improved
Use EMA-based distillation (ablation)MSL · OfficeHome, 10-taskbackward transfer rate: 7.8% vs 12.3%Improved
Increase Mahalanobis metric maximum rank (ablation)MSL · OfficeHome, 10-task, unseen domainsaccuracy: less than 1.5%No clear effect
Increase replay memory size (ablation)Cross-domain continual learning methods · OfficeHome, 10-taskaccuracy: over 5%Improved
Replace Mahalanobis similarity learning with contrastive loss (ablation)MSL · DomainNetaccuracy (%): 63.2 vs 21.2; 51.3 vs 24.7; 61.8 vs 32.8; 55.6 vs 17.2Hurt
Replace Mahalanobis similarity learning with center loss (ablation)MSL · OfficeHomeaccuracy (%): 61.6 vs 46.6; 61.4 vs 44.5; 71.7 vs 58.4; 72.7 vs 52.6Hurt

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