AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Domain Invariant Masked Autoencoders for Self-Supervised Learning from Multi-Domains

Haiyang Yang, Shixiang Tang, Meilin Chen, Yizhou Wang, Feng Zhu, Lei Bai, Rui Zhao, Wanli Ouyang

ECCV 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Masked autoencoder pretraining · 20 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 content-preserved CP-StyleMix instead of no augmentation (ablation)DiMAE · DomainNet Clipart linear eval (ViT-Tiny, 100 epochs)top-1 accuracy: 36.85 -> 48.56Improved
use CP-StyleMix instead of Mixup (ablation)DiMAE · DomainNet Clipart linear eval (ViT-Tiny, 100 epochs)top-1 accuracy: 38.09 -> 48.56Improved
use CP-StyleCut instead of CutMix (ablation)DiMAE · DomainNet Clipart linear eval (ViT-Tiny, 100 epochs)top-1 accuracy: 37.50 -> 47.21Improved
add content-mix Mixup/CutMix instead of no augmentation (ablation)DiMAE · DomainNet Clipart linear eval (ViT-Tiny, 100 epochs)top-1 accuracy: 36.85 -> 38.09No clear effect
add Mixup mixing step after style transfer (ablation)DiMAE · DomainNet Clipart linear eval (ViT-Tiny, 100 epochs)top-1 accuracy: 46.11 -> 48.56Improved
add CutMix mixing step after style transfer (ablation)DiMAE · DomainNet Clipart linear eval (ViT-Tiny, 100 epochs)top-1 accuracy: 46.11 -> 47.21Improved
add multiple domain-specific decoders instead of single decoder (CP-StyleMix) (ablation)DiMAE · DomainNet Clipart linear eval (ViT-Tiny, 100 epochs)top-1 accuracy: 38.09 -> 48.56Improved
add multiple domain-specific decoders instead of single decoder (CP-StyleCut) (ablation)DiMAE · DomainNet Clipart linear eval (ViT-Tiny, 100 epochs)top-1 accuracy: 37.50 -> 47.21Improved
increase decoder depth from 1 to 8 (multi decoders) (ablation)DiMAE · DomainNet Clipart linear eval (ViT-Tiny, 100 epochs)top-1 accuracy: 44.93 -> 48.56Improved
increase decoder depth from 1 to 8 (single decoder) (ablation)MAE-style single decoder · DomainNet Clipart linear eval (ViT-Tiny, 100 epochs)top-1 accuracy: 37.46 -> 38.09No clear effect
increase decoder depth from 8 to 12 (multi decoders) (ablation)DiMAE · DomainNet Clipart linear eval (ViT-Tiny, 100 epochs)top-1 accuracy: 48.56 -> 46.11Hurt
use DiMAE instead of MAE for in-domain pretrainingViT-small · PACS in-domain (linear eval)avg accuracy: 71.2 -> 72.0Improved

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