AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations

Aahlad Manas Puli, Lily H Zhang, Eric Karl Oermann, Rajesh Ranganath

ICLR 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 5 citations (OpenAlex)

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 NURD instead of ERMClass-Conditional Gaussians · Class-Conditional Gaussians, testaccuracy: 39\pm 0 \% -> 58 \pm 0\%Improved
Use NURD instead of ERMColored-MNIST · Colored-MNIST, testaccuracy: 10\pm 0 \% -> 75 \pm 0 \%Improved
Use reweighting NURD instead of ERMWaterbirds · Waterbirds, testaccuracy: 66% -> 83%Improved
Use reweighting NURD instead of ERMChest X-rays · Chest X-rays, testaccuracy: 37% -> 61%Improved
Use generative NURD rather than reweighting NURDColored-MNIST · Colored-MNIST, testaccuracy: 75 \pm 0 \% -> 68 \pm 2\%Hurt
Use generative NURD rather than reweighting NURDWaterbirds · Waterbirds, testaccuracyHurt
Use generative NURD rather than reweighting NURDChest X-rays · Chest X-rays, testaccuracyMixed

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