AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection

Koby Bibas, Meir Feder, Tal Hassner

NeurIPS 2021 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 3 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 pNML regret to BaselineBaseline (DenseNet-BC-100) · CIFAR-100 vs GaussianAUROC: 30.6 -> 100Improved
add pNML regret to BaselineBaseline (ResNet-34) · CIFAR-100 vs GaussianAUROC: 45.0 -> 86.5Improved
add pNML regret to ODINODIN (DenseNet-BC-100) · CIFAR-100 vs LSUN (C)AUROC: 91.5 -> 93.1Improved
add pNML regret to GramGram (DenseNet-BC-100) · CIFAR-100 vs LSUN (C)AUROC: 91.4 -> 94.5Improved
add pNML regret to OECCOECC (DenseNet-BC-100) · CIFAR-100 vs LSUN (C)AUROC: 93.9 -> 96.1Improved
add pNML regret to GramGram (ResNet-34) · CIFAR-100 vs LSUN (C)AUROC: 92.2 -> 94.6Improved
add pNML regret to OECCOECC (ResNet-34) · CIFAR-100 vs LSUN (C)AUROC: 95.7 -> 97.8Improved
add pNML regret to EnergyEnergy (WideResNet-40) · CIFAR-100 vs ImageNet (R)AUROC: 71.4 -> 87.0Improved
add pNML regret to EnergyEnergy (WideResNet-40) · CIFAR-100 vs GaussianTNR at TPR 95%: 9.6 -> 100Improved
add pNML regret to EnergyEnergy (WideResNet-40) · CIFAR-100 vs LSUN (C)AUROC: 95.9 -> 95.5Hurt
add pNML regret to EnergyEnergy (WideResNet-40) · CIFAR-10 vs ImageNet (R)AUROC: 98.1 -> 98.1No clear effect
add pNML regret to BaselineBaseline (ResNet-18) · ImageNet-30 vs CIFAR-10AUROC: 89.99 -> 99.79Improved

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