AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Confidence Estimation Using Unlabeled Data

Chen Li, Xiaoling Hu, Chao Chen

ICLR 2023 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 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
consistency ranking loss (plus correctness ranking loss) added to trainingPreAct-ResNet110 on CIFAR-10 · CIFAR-10 with 2500/5000/10000 labelsAURC: e.g. 109.78 -> 81.50 at 2500 labels; 37.46 -> 28.39 at 10000Improved
consistency ranking loss (plus correctness ranking loss) added to trainingDenseNetBC on CIFAR-100 · CIFAR-100 with 2500/5000/10000 labelsAURC: 214.17 -> 168.57 at 10000 labelsImproved
consistency ranking loss added to segmentation trainingUNet ResNet34 on ISIC2017 · ISIC2017 1/16 (125) labelsAURC: 22.14 (CRL) -> 14.11Improved
consistency ranking loss added to segmentation trainingUNet ResNet34 on ISIC2017 · ISIC2017 full (2000) labelsAURC: CRL 10.17 vs Ours 11.18Hurt
removing correctness ranking loss (ablation)full method on CIFAR-10 (5000 labels) · CIFAR-10 5000 labelsAURC: 47.12 without vs 44.43 with correctness lossImproved
min-max normalization of consistency per labeled/unlabeled batch separately vs unified normalization (ablation)consistency targets · CIFAR-10 5000 labelsAURC: 48.03 (unified) vs 44.43 (separate)Improved
ranking loss instead of point-wise L1 loss on consistency (ablation)confidence output · CIFAR-10 5000 labelsAURC: 76.73 (L1) vs 44.43 (ranking)Improved
lambda_2 perturbation for consistency ranking loss weight (ablation)segmentation on ISIC2017 · ISIC2017confidence estimation metricsNo clear effect
consistency ranking loss on CIFAR-10 minibatch pairsmaximum softmax output · CIFAR-10 unlabeled training setE-AURC: 29.07 (Softmax) -> 19.35 (Softmax ours)Improved

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