AI Paper Atlas

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

Disentangling Masked Autoencoders for Unsupervised Domain Generalization

An Zhang, Han Wang, Xiang Wang, Tat-Seng Chua

ECCV 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Foundation-model domain generalization · 4 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
replace MAE with DisMAE (disentanglement plus adaptive contrastive loss)MAE · DomainNet UDG, 100% labelsAvg. accuracy: 38.75 -> 44.86Improved
replace MAE with DisMAEMAE · DomainNet UDG, 1% labels linear evalAvg. accuracy: 13.68 -> 15.16Improved
DisMAE vs best DG baselineSupervised DG · VLCSAvg. accuracy: 79.26 -> 80.38Improved
DisMAE vs best DG baselineSupervised DG · PACSAvg. accuracy: 85.87 -> 86.37Improved
use intra-domain negatives instead of inter-domain negatives in contrastive loss (ablation)DisMAE · DomainNet ablationAvg. accuracy: 37.01 -> 39.39Improved
add adaptive inverse-probability reweighting from domain classifier (ablation)DisMAE · DomainNet ablationAvg. accuracy: 38.72 -> 39.39Improved
use reversed adaptive weights (ablation)DisMAE · DomainNet ablationAvg. accuracy: 39.39 -> 36.33Hurt
use random weights instead of adaptive weights (ablation)DisMAE · DomainNet ablationAvg. accuracy: 39.39 -> 38.31Hurt
increase decoder depth from 1 to 8 layers (ablation)DisMAE · DomainNet ablationAvg. accuracy: 39.39 -> 36.59Hurt
set mask ratio to 80% rather than 50-70% or 90% (ablation)DisMAE · DomainNet ablationAvg. accuracy: 37.20 -> 39.39 (vs 90%)Improved

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