atlas

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

Selective Classification Can Magnify Disparities Across Groups

ICLR 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 5 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
apply softmax response selective classification to ERM-trained modelsERM models on CelebA · CelebAworst-group selective accuracyHurt
apply softmax response selective classification to ERM-trained modelsERM models across five datasets · CelebA, Waterbirds, CheXpert-device, CivilComments, MultiNLIaverage selective accuracyHelped
apply softmax response selective classification to group DRO modelsgroup DRO models · CelebA, Waterbirds, CheXpert-device, CivilComments, MultiNLIworst-group selective accuracyHelped
train with group DRO instead of ERM (reduces full-coverage group disparity) (ablation)selective classification on standard models · five datasetsworst-group selective accuracyHelped
switch selective confidence from softmax response to Monte Carlo dropout (ablation)ERM selective classifiers · five datasetsworst-group selective accuracyNo 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