AI Paper Atlas

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

MADG: Margin-based Adversarial Learning for Domain Generalization

Aveen Dayal, Vimal K B, Linga Reddy Cenkeramaddi, C Krishna Mohan, Abhinav Kumar, Vineeth N. Balasubramanian

NeurIPS 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Foundation-model domain generalization · 26 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
use margin-based MDD adversarial alignment (MADG) instead of 0-1 loss DANN/CDANNDomainBed · average over 5 datasetsaccuracy (%): 63.8 -> 66.0Improved
MADG versus ERMDomainBed · average over 5 datasetsaccuracy (%): 65.0 -> 66.0Improved
MADG versus best baselines per datasetDomainNet · DomainNetaccuracy (%): 43.4 -> 39.9Hurt
set margin rho_hat to 1.5 instead of 3 (ablation)MADG · PACSaccuracy (%): 85.7 -> 86.5Improved
set margin rho_hat to 1.5 instead of 1 (ablation)MADG · VLCSaccuracy (%): 78.4 -> 78.7No clear effect
use all pairwise MDD classifiers (j=C(N_S,2)) instead of N_S-1 (ablation)MADG · TerraIncognitaaccuracy (%): 51.1 -> 53.7Improved
use all pairwise MDD classifiers instead of N_S-1 (ablation)MADG · VLCS and PACSaccuracy (%): 78.5 -> 78.7; 86.4 -> 86.5No clear effect
use unit weights on MDD losses instead of average or dynamic weights (ablation)MADG · PACSaccuracy (%): 86.1 -> 86.5Improved
MADG versus ERM on Colored MNISTERM · ColoredMNISTaccuracy (%): 57.8 -> 65.6Improved
MADG versus MIRO on OfficeHomeMIRO · OfficeHomeaccuracy (%): 71.1 -> 71.3No clear effect

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