AI Paper Atlas

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

Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization

Wei Zhu, Haitian Zheng, Haofu Liao, Weijian Li, Jiebo Luo

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 29 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 cross-sample estimator I_CS with content representation instead of I_JSD (ablation)CSAD · Colored MNIST (sigma^2=0.020)accuracy: 0.896 -> 0.933Improved
add structural representation alone instead of I_JSD (CSAD-Struc vs AD-JSD) (ablation)CSAD · Colored MNIST (sigma^2=0.020)accuracy: 0.896 -> 0.928Improved
use joint content and structural features instead of content only (ablation)CSAD · Colored MNIST (sigma^2=0.020)accuracy: 0.933 -> 0.943Improved
use joint features instead of structural only (ablation)CSAD · Colored MNIST (sigma^2=0.020)accuracy: 0.928 -> 0.943Improved
add cross-sample debiasing under milder bias (sigma^2=0.050) (ablation)CSAD vs Ruggero et al. · Colored MNIST (sigma^2=0.050)accuracy: 0.982 -> 0.985No clear effect
CSAD vs best baseline Ruggero et al. under severe biasCSAD · Colored MNIST (sigma^2=0.020)accuracy: 0.864 -> 0.943Improved
CSAD vs Kim et al. on IMDB faceCSAD · IMDB face (trained on EB2, test)accuracy: 0.7450 -> 0.7865Improved
CSAD vs Ruggero et al. on IMDB face trained on EB1, testCSAD · IMDB face (trained on EB1, test)accuracy: 0.8720 -> 0.8696No clear effect
CSAD vs LfF on bias-conflicting setCSAD · CelebA BlondHairaccuracy: 0.8340 -> 0.8753Improved
CSAD vs Kim et al. on mPowerCSAD · mPower tappingAUC: 0.759 -> 0.772Improved
increase lambda from 1 to 20 (ablation)CSAD · Adultbalanced accuracy: 81.4 -> 78.9Mixed
CSAD vs baselineCSAD · AdultGap_G RMS: .179 -> .065Improved

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