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

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

18 Oct 2021NeurIPS 2021 12arXiv:2110.09246archive 2025-07-28

Koby Bibas, Meir Feder, Tal Hassner

Detecting out-of-distribution (OOD) samples is vital for developing machine learning based models for critical safety systems. Common approaches for OOD detection assume access to some OOD samples during training which may not be available in a real-life scenario. Instead, we utilize the {\em predictive normalized maximum likelihood} (pNML) learner, in which no assumptions are made on the tested input. We derive an explicit expression of the pNML and its generalization error, denoted as the {\em regret}, for a single layer neural network (NN). We show that this learner generalizes well when (i) the test vector resides in a subspace spanned by the eigenvectors associated with the large eigenvalues of the empirical correlation matrix of the training data, or (ii) the test sample is far from the decision boundary. Furthermore, we describe how to efficiently apply the derived pNML regret to any pretrained deep NN, by employing the explicit pNML for the last layer, followed by the softmax function. Applying the derived regret to deep NN requires neither additional tunable parameters nor extra data. We extensively evaluate our approach on 74 OOD detection benchmarks using DenseNet-100, ResNet-34, and WideResNet-40 models trained with CIFAR-100, CIFAR-10, SVHN, and ImageNet-30 showing a significant improvement of up to 15.6\% over recent leading methods.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

kobybibas/pnml_ood_detection officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Out of Distribution (OOD) DetectionOut-of-Distribution Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Out-of-Distribution Detection CIFAR-10 vs Gaussian DenseNet-BC-100 AUROC 100 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs Gaussian ResNet-34 AUROC 100 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs ImageNet (C) DenseNet-BC-100 AUROC 99.9 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs ImageNet (C) ResNet-34 AUROC 99.8 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs ImageNet (R) DenseNet-BC-100 AUROC 99.9 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs ImageNet (R) ResNet-34 AUROC 99.9 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs LSUN (C) DenseNet-BC-100 AUROC 99.9 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs LSUN (C) ResNet-34 AUROC 99.5 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs LSUN (R) ResNet-34 AUROC 100 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs LSUN (R) DenseNet-BC-100 AUROC 100 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs SVHN DenseNet-BC-100 AUROC 100 #1 of 3 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs SVHN ResNet-34 AUROC 99.8 #3 of 3 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs Uniform DenseNet-BC-100 AUROC 100 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs Uniform ResNet-34 AUROC 100 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs iSUN DenseNet-BC-100 AUROC 100 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs iSUN ResNet-34 AUROC 100 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 vs Gaussian DenseNet-BC-100 AUROC 100 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 vs Gaussian ResNet-34 AUROC 100 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 vs ImageNet (C) DenseNet-BC-100 AUROC 99.0 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 vs ImageNet (C) ResNet-34 AUROC 98.4 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 vs ImageNet (R) DenseNet-BC-100 AUROC 99.5 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 vs ImageNet (R) ResNet-34 AUROC 99.2 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 vs LSUN (C) ResNet-34 AUROC 97.8 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 vs LSUN (C) DenseNet-BC-100 AUROC 96.1 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 vs LSUN (R) DenseNet-BC-100 AUROC 99.7 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 vs LSUN (R) ResNet-34 AUROC 99.6 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 vs SVHN DenseNet-BC-100 AUROC 98.4 #2 of 5 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 vs SVHN ResNet-34 AUROC 97.9 #3 of 5 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 vs Uniform DenseNet-BC-100 AUROC 100 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 vs Uniform ResNet-34 AUROC 100 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 vs iSUN DenseNet-BC-100 AUROC 99.5 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 vs iSUN ResNet-34 AUROC 99.3 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection SVHN vs CIFAR-10 DenseNet-BC-100 AUROC 100 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection SVHN vs CIFAR-10 ResNet-34 AUROC 99.8 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection SVHN vs CIFAR-100 DenseNet-BC-100 AUROC 100 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection SVHN vs CIFAR-100 ResNet-34 AUROC 99.8 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection SVHN vs Gaussian DenseNet-BC-100 AUROC 100 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection SVHN vs Gaussian ResNet-34 AUROC 100 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection SVHN vs ImageNet (C) DenseNet-BC-100 AUROC 100 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection SVHN vs ImageNet (C) ResNet-34 AUROC 100 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection SVHN vs ImageNet (R) DenseNet-BC-100 AUROC 100 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection SVHN vs ImageNet (R) ResNet-34 AUROC 100 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection SVHN vs LSUN (C) DenseNet-BC-100 AUROC 100 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection SVHN vs LSUN (C) ResNet-34 AUROC 99.9 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection SVHN vs LSUN (R) DenseNet-BC-100 AUROC 100 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection SVHN vs LSUN (R) ResNet-34 AUROC 100 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection SVHN vs Uniform DenseNet-BC-100 AUROC 100 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection SVHN vs Uniform ResNet-34 AUROC 100 #2 of 2 Archive leaderboard report
Out-of-Distribution Detection SVHN vs iSUN DenseNet-BC-100 AUROC 100 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection SVHN vs iSUN ResNet-34 AUROC 100 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Test

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections