AI Paper Atlas

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

Understanding the Feature Norm for Out-of-Distribution Detection

Jaewoo Park, Jacky Chen Long Chai, Jaeho Yoon, Andrew Beng Jin Teoh

ICCV 2023 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 26 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 sparsity term to the l1 feature norm (NAN) (ablation)feature norm on ResNet-50 with projection head · ImageNet-1k OOD (avg)AUROC: 57.99 -> 92.32Improved
add sparsity term to the l1 feature norm (NAN) (ablation)feature norm on ResNet-18 CIFAR-10 · CIFAR-10 OOD (avg)AUROC: 92.40 -> 94.90Improved
add sparsity term when no projection head is used (ablation)NAN on ResNet-50 average pool layer · ImageNet-1k OOD (avg)AUROC: 87.09 -> 86.33Hurt
apply NAN on projection-head hidden layer instead of average pool (ablation)NAN on ResNet-18 CIFAR-10 · CIFAR-10 OOD (avg)FPR95: 38.86 -> 30.08Improved
combine NAN with KNN, SSD and ReActNAN · ImageNet-1k OOD (avg)AUROC: 92.32 -> 94.61Improved
combine NAN with KNN in one-class classificationKNN · CIFAR-10 one-classAUROC: 92.1 -> 94.3Improved
combine NAN with SSD in one-class classificationSSD · CIFAR-100 one-classAUROC: 85.7 -> 88.7Improved
use NAN instead of distance-based detectors on far-OOD TextureNAN · ImageNet-1k TextureAUROC: 88.09 vs 96.96 (SSD)Hurt
increase last hidden layer dimension (ablation)NAN on ResNet-18 CIFAR-10 · CIFAR-10 OODAUROC/FPR95Improved
train with discriminative labels (supervised, instance, random) vs one label for all (ablation)feature norm on ResNet-18 CIFAR-10 · CIFAR-10 OODAUROCImproved

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