AI Paper Atlas

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

A Conservative Approach for Unbiased Learning on Unknown Biases

Myeongho Jeon, Daekyung Kim, Woochul Lee, Myungjoo Kang, Joonseok Lee

CVPR 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 12 citations (OpenAlex)

Check 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
Use UBNet instead of the base classifierVGG11 on CelebA-HQ · val-EB1accuracy: 99.38(±0.31) -> 99.18(±0.18)No clear effect
Use UBNet instead of the base classifierVGG11 on CelebA-HQ · val-EB2accuracy: 51.22(±1.73) -> 58.22(±0.64)Improved
Use UBNet instead of the base classifierVGG11 on CelebA-HQ · test setaccuracy: 75.30(±0.93) -> 78.70(±0.24)Improved
Use UBNet instead of the strongest listed baselineResNet18 on UTKFace skin tone prediction · trained on UB1, evaluated on UB2accuracy: 79.35(±0.17) -> 83.67(±1.05)Improved
Use UBNet instead of the strongest listed baselineResNet18 on UTKFace skin tone prediction · trained on UB1, test setaccuracy: 85.07(±0.46) -> 87.25(±0.82)Improved
Use UBNet instead of the strongest listed baselineResNet18 on UTKFace skin tone prediction · trained on UB2, evaluated on UB1accuracy: 80.82(±0.15) -> 84.29(±1.24)Improved
Use UBNet instead of the strongest listed baselineResNet18 on UTKFace skin tone prediction · trained on UB2, test setaccuracy: 85.88(±0.27) -> 87.94(±0.80)Improved
Use UBNet instead of the strongest listed baselineResNet18 on UTKFace gender prediction · trained on UB1, evaluated on UB2accuracy: 82.02(±0.84) -> 82.07(±1.55)No clear effect
Use UBNet instead of the strongest listed baselineResNet18 on UTKFace gender prediction · trained on UB1, test setaccuracy: 83.67(±0.73) -> 87.75(±0.58)Improved
Add hierarchical features, group convolution, and orthogonal regularization (ablation)VGG11-based classifier on CelebA-HQ · test setaccuracy: 76.11 -> 78.70Improved
Add group convolution to the hierarchical-feature model (ablation)VGG11-based classifier on CelebA-HQ · test setaccuracy: 77.72 -> 77.93Improved
Add orthogonal regularization to hierarchical features and group convolution (ablation)VGG11-based classifier on CelebA-HQ · test setaccuracy: 77.93 -> 78.70Improved

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