AI Paper Atlas

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

Discover the Unknown Biased Attribute of an Image Classifier

Zhiheng Li, Chenliang Xu

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 40 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 orthogonalization penalty (ablation)total variation loss method · SmallNORBDelta cos: -0.02 -> 0.12Improved
add orthogonalization penalty (ablation)total variation loss method · dSpritesDelta cos: -0.01 -> 0.05Improved
add orthogonalization penalty (ablation)total variation loss method · SmallNORB|cos(w_b_hat,w_t)|: 0.27 -> 0.10Improved
add orthogonalization penalty (ablation)total variation loss method · dSprites|cos(w_b_hat,w_t)|: 0.21 -> 0.13Improved
add orthogonalization penalty (ablation)total variation loss method · SmallNORB|cos(w_b_hat,w_b)|: 0.25 -> 0.23Hurt
add orthogonalization penalty (ablation)total variation loss method · dSprites|cos(w_b_hat,w_b)|: 0.20 -> 0.17Hurt
add Hessian Penalty to full method (ablation)Ours · SmallNORBDelta cos: 0.12 -> 0.10Hurt
add Hessian Penalty to full method (ablation)Ours · dSpritesDelta cos: 0.05 -> 0.01Hurt
add Hessian Penalty to full method (ablation)Ours · SmallNORB|cos(w_b_hat,w_t)|: 0.10 -> 0.15Hurt
add Hessian Penalty to full method (ablation)Ours · SmallNORB|cos(w_b_hat,w_b)|: 0.23 -> 0.25Improved
use proposed method instead of Hessian Penaltyunsupervised hyperplane discovery · CelebADelta cos: 0.0005 -> 0.06Improved
use proposed method instead of Hessian Penaltyunsupervised hyperplane discovery · FFHQDelta cos: 0.03 -> 0.17Improved

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