Papers › Deep Anomaly Detection with Outlier Exposure

Deep Anomaly Detection with Outlier Exposure

11 Dec 2018ICLR 2019 5arXiv:1812.04606archive 2025-07-28

Dan Hendrycks, Mantas Mazeika, Thomas Dietterich

It is important to detect anomalous inputs when deploying machine learning systems. The use of larger and more complex inputs in deep learning magnifies the difficulty of distinguishing between anomalous and in-distribution examples. At the same time, diverse image and text data are available in enormous quantities. We propose leveraging these data to improve deep anomaly detection by training anomaly detectors against an auxiliary dataset of outliers, an approach we call Outlier Exposure (OE). This enables anomaly detectors to generalize and detect unseen anomalies. In extensive experiments on natural language processing and small- and large-scale vision tasks, we find that Outlier Exposure significantly improves detection performance. We also observe that cutting-edge generative models trained on CIFAR-10 may assign higher likelihoods to SVHN images than to CIFAR-10 images; we use OE to mitigate this issue. We also analyze the flexibility and robustness of Outlier Exposure, and identify characteristics of the auxiliary dataset that improve performance.

PaperPDFConference PDFCodeCode Syntology ran

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.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1812.04606")

Code

Syntology Ran 5 of 5 code samples harvested from 4 repositories linked to this paper; 0 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 3 ran with no contract checked.

By repository: community (archive-listed): 5 samples from 4 repositories, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

hendrycks/outlier-exposure officialmentioned in papermentioned on GitHubpytorch report
AlexMeinke/Provable-OOD-Detection mentioned on GitHubpytorch report
albertkx/conal mentioned on GitHubpytorch report
guyAmit/GLOD mentioned on GitHubpytorch report
jun-cen/unified_open_set_recognition mentioned on GitHubpytorch report
oliverzhang42/ood_medical_images mentioned on GitHubpytorch report
sayakpaul/Generalized-ODIN-TF mentioned on GitHubtfApache-2.0 report
zjysteven/mixoe mentioned 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

5 samples harvested; 5 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
3ran

Licence: 4 of the 5 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

GaussianLayer guyAmit/GLOD/FOOD/Gaussain_layer.py community (archive-listed) ran no licence file found · pointer only · 04a6bca8fa7ea2c2 · report
OELoss AlexMeinke/Provable-OOD-Detection/utils/traintest/losses.py community (archive-listed) ran fingerprinted MIT (permissive) · 7e2caa67572f6723 · report
OE_300k_dataloader jun-cen/unified_open_set_recognition/UOSR_train/bit_pytorch/oe_bit.py community (archive-listed) ran no licence file found · pointer only · a720f50e53abe705 · report
get_loss_baseline oliverzhang42/ood_medical_images/src/losses.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 40f6f2dd97282786 · report
get_loss_outlier_exposure oliverzhang42/ood_medical_images/src/losses.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 9a2f19557ae1a813 · report

Tasks

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

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Out-of-Distribution Detection CIFAR-10 WRN 40-2 + OE AUROC 97.8 #8 of 10 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 WRN 40-2 + OE FPR95 9.50 #8 of 10 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 WRN 40-2 (MSP Baseline) AUROC 97.8 #9 of 10 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 WRN 40-2 (MSP Baseline) FPR95 34.94 #9 of 10 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs CIFAR-100 WRN 40-2 + OE AUPR 76.2 #10 of 14 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs CIFAR-100 WRN 40-2 + OE AUROC 93.3 #10 of 14 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 WRN 40-2 + OE FPR95 38.50 #3 of 4 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 WRN 40-2 (MSP Baseline) FPR95 62.66 #4 of 4 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 vs SVHN OE AUROC 86.9 #5 of 5 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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