Papers › Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images

Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images

23 May 2022arXiv:2205.11474archive 2025-07-28

Philipp Liznerski, Lukas Ruff, Robert A. Vandermeulen, Billy Joe Franks, Klaus-Robert Müller, Marius Kloft

Due to the intractability of characterizing everything that looks unlike the normal data, anomaly detection (AD) is traditionally treated as an unsupervised problem utilizing only normal samples. However, it has recently been found that unsupervised image AD can be drastically improved through the utilization of huge corpora of random images to represent anomalousness; a technique which is known as Outlier Exposure. In this paper we show that specialized AD learning methods seem unnecessary for state-of-the-art performance, and furthermore one can achieve strong performance with just a small collection of Outlier Exposure data, contradicting common assumptions in the field of AD. We find that standard classifiers and semi-supervised one-class methods trained to discern between normal samples and relatively few random natural images are able to outperform the current state of the art on an established AD benchmark with ImageNet. Further experiments reveal that even one well-chosen outlier sample is sufficient to achieve decent performance on this benchmark (79.3% AUC). We investigate this phenomenon and find that one-class methods are more robust to the choice of training outliers, indicating that there are scenarios where these are still more useful than standard classifiers. Additionally, we include experiments that delineate the scenarios where our results hold. Lastly, no training samples are necessary when one uses the representations learned by CLIP, a recent foundation model, which achieves state-of-the-art AD results on CIFAR-10 and ImageNet in a zero-shot setting.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 1 code sample harvested from 1 repository linked to this paper: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

liznerski/eoe officialmentioned in paperpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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

1 sample harvested: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran

Licence: 0 of the 1 sample 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 liznerski/eoe. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

liznerski/eoe official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
global_contrast_normalization src/eoe/datasets/bases.py ran MIT (permissive) · 95ff8c10f19afc85 · report fixture: signature x:Tensor/2/float, scale:str/0/str · returned Tensor · level recorded 2026-09-24

Tasks

Anomaly Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection Leave-One-Class-Out CIFAR-10 BCE-CLIP AUROC 98.4 #1 of 6 Archive leaderboard report
Anomaly Detection Leave-One-Class-Out CIFAR-10 CLIP (zero shot) AUROC 92.2 #2 of 6 Archive leaderboard report
Anomaly Detection Leave-One-Class-Out CIFAR-10 Binary Cross Entropy (OE) AUROC 86.6 #3 of 6 Archive leaderboard report
Anomaly Detection Leave-One-Class-Out CIFAR-10 HSC AUROC 84.8 #4 of 6 Archive leaderboard report
Anomaly Detection Leave-One-Class-Out CIFAR-10 DSAD AUROC 84.2 #5 of 6 Archive leaderboard report
Anomaly Detection Leave-One-Class-Out CIFAR-10 DSVDD AUROC 52.2 #6 of 6 Archive leaderboard report
Anomaly Detection Leave-One-Class-Out ImageNet-30 BCE-CLIP (OE) AUROC 99.3 #1 of 6 Archive leaderboard report
Anomaly Detection Leave-One-Class-Out ImageNet-30 CLIP (zero shot) AUROC 97.8 #2 of 6 Archive leaderboard report
Anomaly Detection Leave-One-Class-Out ImageNet-30 DSAD AUROC 88.8 #3 of 6 Archive leaderboard report
Anomaly Detection Leave-One-Class-Out ImageNet-30 HSC (OE) AUROC 88.3 #4 of 6 Archive leaderboard report
Anomaly Detection Leave-One-Class-Out ImageNet-30 Binary Cross Entropy (OE) AUROC 88.2 #5 of 6 Archive leaderboard report
Anomaly Detection Leave-One-Class-Out ImageNet-30 DSVDD AUROC 49.7 #6 of 6 Archive leaderboard report
Anomaly Detection One-class CIFAR-10 CLIP (OE) AUROC 99.6 #1 of 36 Archive leaderboard report
Anomaly Detection One-class CIFAR-10 CLIP (zero shot) AUROC 98.5 #7 of 36 Archive leaderboard report
Anomaly Detection One-class ImageNet-30 BCE-Clip (OE) AUROC 99.90 #1 of 11 Archive leaderboard report
Anomaly Detection One-class ImageNet-30 CLIP (Zero Shot) AUROC 99.88 #2 of 11 Archive leaderboard report
Anomaly Detection One-class ImageNet-30 Binary Cross Entropy (OE) AUROC 97.7 #3 of 11 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

CLIP

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