AI Paper Atlas

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

Self-training Avoids Using Spurious Features Under Domain Shift

Yining Chen, Colin Wei, Ananya Kumar, Tengyu Ma

NeurIPS 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 5 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 self-training on unlabeled target datasource classifier · CelebAaccuracy (%): 81\% -> 88\%Improved
add self-training on unlabeled target datasource classifier · CMNIST10 (p = 0.95)accuracy (%): 82\% -> 91\%Improved
add self-training on unlabeled target datasource classifier · CMNIST2accuracy (%): 94\% -> 96\%Improved
add self-training when source classifier is poor (spurious correlation raised to 0.97)source classifier · CMNIST10 (p = 0.97)accuracy (%): 72\% -> 67\%Hurt
raise color-label correlation in source from 0.95 to 0.97 (ablation)source classifier · CMNIST10 targetaccuracy (%): 82\% -> 72\%Hurt

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