AI Paper Atlas

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

Learning to Balance Specificity and Invariance for In and Out of Domain Generalization

Prithvijit Chattopadhyay, Yogesh Balaji, Judy Hoffman

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 195 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 domain-specific masks with soft-IoU loss (DMG)Aggregate baseline, AlexNet · DomainNet out-of-domainoverall accuracy: 28.60 -> 31.15Improved
add domain-specific masks (DMG)Aggregate, ResNet-50 · DomainNet out-of-domainoverall accuracy: 44.00 -> 43.63No clear effect
add domain-specific masks (DMG)Aggregate*, ResNet-50 · PACSoverall accuracy: 78.38 -> 83.37Improved
add domain-specific masks (DMG)Aggregate*, AlexNet · PACSoverall accuracy: 68.38 -> 73.32Improved
use known-domain mask at test time (DMG-KD) instead of averaging masksDMG, AlexNet · DomainNet in-domainoverall accuracy: 52.30 -> 54.54Improved
use known-domain mask at test time (DMG-KD)DMG, ResNet-18 · DomainNet in-domainoverall accuracy: 59.37 -> 60.59Improved
use known-domain mask at test time (DMG-KD)DMG, ResNet-50 · DomainNet in-domainoverall accuracy: 63.79 -> 65.14Improved
use matching source-domain mask rather than mismatched mask (ablation)DMG, AlexNet · DomainNet I,P,Q,R,S->C, source Infographaccuracy: 18.42 -> 23.84Improved
use matching source-domain mask rather than mismatched mask (ablation)DMG, AlexNet · DomainNet C,I,P,R,S->Q, source Clipartaccuracy: 59.62 -> 66.70Improved
average predictions of all masks (Pred-Ens) vs averaging masks (Mask-Ens) (ablation)DMG, AlexNet · DomainNet out-of-domainoverall accuracy: 31.15 -> 31.10No clear effect
average predictions of all masks (Pred-Ens) vs averaging masks (Mask-Ens) (ablation)DMG, AlexNet · DomainNet in-domainoverall accuracy: 52.30 -> 52.17No clear effect
increase soft-IoU weight lambda_O up to 0.1 and 1 (ablation)DMG, AlexNet · DomainNetin-domain and out-of-domain accuracy: only minor variations, slight drop in in-domain at 0.1 and 1No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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