AI Paper Atlas

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

Delving into Identify-Emphasize Paradigm for Combating Unknown Bias

Bowen Zhao, Chen Chen, Qian-Wei Wang, Anfeng He, Shu‐Tao Xia

IJCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 2 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 self-supervised pretext tasks (ablation)ECS+GA · Corrupted CIFAR10-1 (rho=99.5%)unbiased accuracy: 34.3 -> 44.5Improved
add self-supervised pretext tasks (ablation)Vanilla · Corrupted CIFAR10-1 (rho=99.5%)unbiased accuracy: 15.6 -> 23.7Improved
add confident-picking to epoch-ensemble scoring (ablation)ECS · Colored MNIST (rho=98%)average precision: 53.8 -> 95.0Improved
add peer model (ablation)ECS · Colored MNIST (rho=98%)average precision: 95.0 -> 98.8Improved
add peer model and confident-picking (ablation)ECS · Biased CelebAaverage precision: 46.5 -> 67.6Improved
add epoch-ensemble to GCE scoring (ablation)LfF GCE · Colored MNIST (rho=98%)average precision: 37.0 -> 89.3Improved
score with ECS instead of vanilla model (ablation)GA · Colored MNIST (rho=98%)unbiased accuracy: 49.2 -> 89.5Improved
train GA on all samples rather than only bias-aligned ones (ablation)GA · Colored MNIST (rho=98%)unbiased accuracy: 80.9 -> 89.1Improved
train GA on all samples rather than only bias-conflicting ones (ablation)GA · Colored MNIST (rho=98%)unbiased accuracy: 87.5 -> 89.1Improved
replace Rew with GA under very few bias-conflicting samplesRew · Colored MNIST (rho=99.95%)unbiased accuracy: 22.9 -> 53.9Improved
evaluate at last epoch instead of best epochLfF · Colored MNIST (rho=99%)unbiased accuracy: 80.3 -> 68.8Hurt
evaluate at last epoch instead of best epochECS+GA · Colored MNIST (rho=99%)unbiased accuracy: 86.4 -> 84.6Hurt

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