Papers › Exploring the Limits of Out-of-Distribution Detection
Exploring the Limits of Out-of-Distribution Detection
Stanislav Fort, Jie Ren, Balaji Lakshminarayanan
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.
In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Out-of-Distribution Detection | CIFAR-10 vs CIFAR-100 | R+ViT finetuned on CIFAR-10 | AUPR | 97.75 | #2 of 14 | Archive leaderboard | report |
| Out-of-Distribution Detection | CIFAR-10 vs CIFAR-100 | R+ViT finetuned on CIFAR-10 | AUROC | 98.52 | #2 of 14 | Archive leaderboard | report |
| Out-of-Distribution Detection | CIFAR-10 vs CIFAR-100 | ViT finetuned on CIFAR-10 | AUPR | 97.68 | #3 of 14 | Archive leaderboard | report |
| Out-of-Distribution Detection | CIFAR-10 vs CIFAR-100 | ViT finetuned on CIFAR-10 | AUROC | 98.42 | #3 of 14 | Archive leaderboard | report |
| Out-of-Distribution Detection | CIFAR-10 vs CIFAR-100 | MLP-Mixer finetuned on CIFAR-10 | AUPR | 96.28 | #4 of 14 | Archive leaderboard | report |
| Out-of-Distribution Detection | CIFAR-10 vs CIFAR-100 | MLP-Mixer finetuned on CIFAR-10 | AUROC | 97.85 | #4 of 14 | Archive leaderboard | report |
| Out-of-Distribution Detection | CIFAR-100 vs CIFAR-10 | Ensemble of ViTs | AUROC | 98.11 | #2 of 14 | Archive leaderboard | report |
| Out-of-Distribution Detection | CIFAR-100 vs CIFAR-10 | ViT-L_16 finetuned on CIFAR-100 | AUROC | 97.98 | #3 of 14 | Archive leaderboard | report |
| Out-of-Distribution Detection | CIFAR-100 vs CIFAR-10 | R50+ViT_B-16 finetuned on CIFAR-100 | AUPR | 92.08 | #4 of 14 | Archive leaderboard | report |
| Out-of-Distribution Detection | CIFAR-100 vs CIFAR-10 | R50+ViT_B-16 finetuned on CIFAR-100 | AUROC | 96.23 | #4 of 14 | Archive leaderboard | report |
| Out-of-Distribution Detection | CIFAR-100 vs CIFAR-10 | ViT_B-16 finetuned on CIFAR-100 | AUPR | 91.89 | #5 of 14 | Archive leaderboard | report |
| Out-of-Distribution Detection | CIFAR-100 vs CIFAR-10 | ViT_B-16 finetuned on CIFAR-100 | AUROC | 95.53 | #5 of 14 | Archive leaderboard | report |
| Out-of-Distribution Detection | CIFAR-100 vs CIFAR-10 | MLP-Mixer_B-16 finetuned on CIFAR-100 | AUPR | 90.22 | #6 of 14 | Archive leaderboard | report |
| Out-of-Distribution Detection | CIFAR-100 vs CIFAR-10 | MLP-Mixer_B-16 finetuned on CIFAR-100 | AUROC | 95.31 | #6 of 14 | Archive leaderboard | report |
| Out-of-Distribution Detection | CIFAR-100 vs CIFAR-10 | CLIP using class name words describing the two distributions | AUROC | 94.68 | #7 of 14 | 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
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