AI Paper Atlas

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

Learning from Failure: De-biasing Classifier from Biased Classifier

Junhyun Nam, Hyuntak Cha, Sungsoo Ahn, Jaeho Lee, Jinwoo Shin

NeurIPS 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 95 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
LfF reweighting by biased-model relative difficultyVanilla classifier · Colored MNIST 99.5%unbiased accuracy: 35.34 -> 63.39Improved
LfF reweightingVanilla classifier · Corrupted CIFAR-10^1 99%unbiased accuracy: 22.72 -> 41.37Improved
LfF (no bias labels) vs Group DRO (bias labels)debiasing · Corrupted CIFAR-10^2 99.5%unbiased accuracy: 34.25 -> 34.11No clear effect
LfF vs Group DROdebiasing · CelebAunbiased accuracy: HairColor 85.43 -> 84.24; HeavyMakeup 64.88 -> 66.20Mixed
LfF vs ReBiasdebiasing · BAR Divingaccuracy: 51.57 -> 34.59Hurt
train biased model with GCE instead of CE (ablation)LfF · Colored MNIST 99%unbiased accuracy: 49.90 -> 74.01Improved
train biased model with GCE instead of CE (ablation)LfF · Corrupted CIFAR-10^1 99%unbiased accuracy: 25.15 -> 41.37Improved
swap target/bias so bias is harder than targetVanilla classifier · Colored MNISTunbiased accuracy: -0.03%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