AI Paper Atlas

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

Towards Debiasing DNN Models from Spurious Feature Influence

Mengnan Du, Ruixiang Tang, Weijie Fu, Xia Hu

AAAI 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 4 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
Counter-teach the student using a bias-only race teacherMEPS MLP · MEPS (race)demographic parity: 0.857 -> 0.950Improved
Counter-teach the student using a bias-only race teacherMEPS MLP · MEPS (race)equality of opportunity: -0.195 -> -0.057Improved
Counter-teach the student using a bias-only race teacherMEPS MLP · MEPS (race)equality of odds: -0.243 -> -0.070Improved
Counter-teach the student using a bias-only race teacherMEPS MLP · MEPS (gender)equality of opportunity: -0.052 -> -0.081Hurt
Train separate teachers for race and genderMEPS MLP · MEPS (race and gender)equality of odds: Race: -0.243 -> -0.076; gender: -0.076 -> -0.036Improved
Train separate teachers for race and genderMEPS MLP · MEPSaccuracy: 86.5 -> 84.2Hurt
Add explicit interpretation decorrelation (ablation)DeFI on MEPS · MEPS (race)demographic parity: 0.857 -> 0.956Improved
Add explicit interpretation decorrelation (ablation)DeFI on MEPS · MEPS (race)equality of opportunity: -0.195 -> -0.061Improved
Add explicit interpretation decorrelation (ablation)DeFI on MEPS · MEPSaccuracy: 86.5 -> 84.3Hurt
Add implicit ensemble decorrelation (ablation)DeFI on MEPS · MEPS (race)equality of opportunity: -0.195 -> -0.037Improved
Add implicit ensemble decorrelation (ablation)DeFI on MEPS · MEPSaccuracy: 86.5 -> 86.0No 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