AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Improving Out-of-Distribution Robustness via Selective Augmentation

Huaxiu Yao, Yu Wang, Sai Li, Linjun Zhang, Weixin Liang, James Zou, Chelsea Finn

ICML 2022 · Label-efficient and robust learning › Test-time adaptation · approach: Robust optimization for distribution shift · 21 citations (OpenAlex)

This paper tried a common change: Add mixup or CutMix

use vanilla mixup instead of LISA's selective pairing · Camelyon17, FMoW, RxRx1, Amazon, MetaShift · dataset evaluation metric: 71.2 $\pm$ 5.3\% vs. 77.1 $\pm$ 6.5\%; 34.2 $\pm$ 0.45\% vs. 35.5 $\pm$ 0.65\%; 26.5 $\pm$ 0.5\% vs. 31.9 $\pm$ 0.8\%; 5 Mixed

What 547 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 selective interpolation across same-label/different-domain or same-domain/different-label pairs rather than vanilla mixup (ablation)LISA · CMNISTworst-group accuracy: 3.1% -> 73.3%Improved
use selective interpolation across same-label/different-domain or same-domain/different-label pairs rather than vanilla mixup (ablation)LISA · Waterbirdsworst-group accuracy: 56.2% -> 89.2%Improved
use selective interpolation across same-label/different-domain or same-domain/different-label pairs rather than vanilla mixup (ablation)LISA · CelebAworst-group accuracy: 46.4% -> 89.3%Improved
use selective interpolation across same-label/different-domain or same-domain/different-label pairs rather than vanilla mixup (ablation)LISA · CivilCommentsworst-group accuracy: 67.2% -> 72.6%Improved
interpolate samples from the same label but different domains (ablation)LISA · CMNIST, Waterbirds, CelebAworst-group accuracyImproved
interpolate samples from the same domain but different labels (ablation)LISA · CMNIST, Waterbirds, CelebAworst-group accuracyImproved
restrict interpolation to samples sharing both label and domain (ablation)mixup for OOD robustness · CMNIST, Waterbirds, CelebA, CivilCommentsworst-group accuracy: LISA 73.3% vs. 24.0% (CMNIST); 89.2% vs. 68.0% (Waterbirds); 89.3% vs. 58.3% (CelebA); 72.6% vs. 69.2% (CivilComments)Hurt
use vanilla mixup instead of LISA's selective pairing (ablation)LISA · Camelyon17, FMoW, RxRx1, Amazon, MetaShiftdataset evaluation metric: 71.2 $\pm$ 5.3\% vs. 77.1 $\pm$ 6.5\%; 34.2 $\pm$ 0.45\% vs. 35.5 $\pm$ 0.65\%; 26.5 $\pm$ 0.5\% vs. 31.9 $\pm$ 0.8\%; 5Mixed
increase the training-to-test domain distanceLISA versus best baseline · MetaShiftworst-group accuracy gain over best baseline: +1.5%, +1.2%, +3.6%, +9.6%Improved
balance groups to remove spurious correlations (ablation)LISA · CMNIST, Waterbirds, CelebAaccuracy: ERM 73.67%, 88.07%, 86.11%; LISA 73.18%, 87.05%, 87.22%No 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