TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Exploring the Limits of Out-of-Distribution Detection

Exploring the Limits of Out-of-Distribution Detection

Stanislav Fort, Jie Ren, Balaji Lakshminarayanan

2021-06-06NeurIPS 2021 12Unsupervised Pre-trainingOut of Distribution (OOD) DetectionOut-of-Distribution Detection
PaperPDFCode

Abstract

Near out-of-distribution detection (OOD) is a major challenge for deep neural networks. We demonstrate that large-scale pre-trained transformers can significantly improve the state-of-the-art (SOTA) on a range of near OOD tasks across different data modalities. For instance, on CIFAR-100 vs CIFAR-10 OOD detection, we improve the AUROC from 85% (current SOTA) to more than 96% using Vision Transformers pre-trained on ImageNet-21k. On a challenging genomics OOD detection benchmark, we improve the AUROC from 66% to 77% using transformers and unsupervised pre-training. To further improve performance, we explore the few-shot outlier exposure setting where a few examples from outlier classes may be available; we show that pre-trained transformers are particularly well-suited for outlier exposure, and that the AUROC of OOD detection on CIFAR-100 vs CIFAR-10 can be improved to 98.7% with just 1 image per OOD class, and 99.46% with 10 images per OOD class. For multi-modal image-text pre-trained transformers such as CLIP, we explore a new way of using just the names of outlier classes as a sole source of information without any accompanying images, and show that this outperforms previous SOTA on standard vision OOD benchmark tasks.

Results

TaskDatasetMetricValueModel
Out-of-Distribution DetectionCIFAR-10 vs CIFAR-100AUPR97.75R+ViT finetuned on CIFAR-10
Out-of-Distribution DetectionCIFAR-10 vs CIFAR-100AUROC98.52R+ViT finetuned on CIFAR-10
Out-of-Distribution DetectionCIFAR-10 vs CIFAR-100AUPR97.68ViT finetuned on CIFAR-10
Out-of-Distribution DetectionCIFAR-10 vs CIFAR-100AUROC98.42ViT finetuned on CIFAR-10
Out-of-Distribution DetectionCIFAR-10 vs CIFAR-100AUPR96.28MLP-Mixer finetuned on CIFAR-10
Out-of-Distribution DetectionCIFAR-10 vs CIFAR-100AUROC97.85MLP-Mixer finetuned on CIFAR-10
Out-of-Distribution DetectionCIFAR-100 vs CIFAR-10AUROC98.11Ensemble of ViTs
Out-of-Distribution DetectionCIFAR-100 vs CIFAR-10AUROC97.98ViT-L_16 finetuned on CIFAR-100
Out-of-Distribution DetectionCIFAR-100 vs CIFAR-10AUPR92.08R50+ViT_B-16 finetuned on CIFAR-100
Out-of-Distribution DetectionCIFAR-100 vs CIFAR-10AUROC96.23R50+ViT_B-16 finetuned on CIFAR-100
Out-of-Distribution DetectionCIFAR-100 vs CIFAR-10AUPR91.89ViT_B-16 finetuned on CIFAR-100
Out-of-Distribution DetectionCIFAR-100 vs CIFAR-10AUROC95.53ViT_B-16 finetuned on CIFAR-100
Out-of-Distribution DetectionCIFAR-100 vs CIFAR-10AUPR90.22MLP-Mixer_B-16 finetuned on CIFAR-100
Out-of-Distribution DetectionCIFAR-100 vs CIFAR-10AUROC95.31MLP-Mixer_B-16 finetuned on CIFAR-100
Out-of-Distribution DetectionCIFAR-100 vs CIFAR-10AUROC94.68CLIP using class name words describing the two distributions

Related Papers

ZClassifier: Temperature Tuning and Manifold Approximation via KL Divergence on Logit Space2025-07-14Safe Domain Randomization via Uncertainty-Aware Out-of-Distribution Detection and Policy Adaptation2025-07-08FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution Detection2025-07-06Out-of-distribution detection in 3D applications: a review2025-07-01Generative Adversarial Evasion and Out-of-Distribution Detection for UAV Cyber-Attacks2025-06-26Enclosing Prototypical Variational Autoencoder for Explainable Out-of-Distribution Detection2025-06-17A Variational Information Theoretic Approach to Out-of-Distribution Detection2025-06-17FindMeIfYouCan: Bringing Open Set metrics to $\textit{near} $, $ \textit{far} $ and $\textit{farther}$ Out-of-Distribution Object Detection2025-06-16