Papers › Anomaly Detection Requires Better Representations

Anomaly Detection Requires Better Representations

19 Oct 2022arXiv:2210.10773archive 2025-07-28

Tal Reiss, Niv Cohen, Eliahu Horwitz, Ron Abutbul, Yedid Hoshen

Anomaly detection seeks to identify unusual phenomena, a central task in science and industry. The task is inherently unsupervised as anomalies are unexpected and unknown during training. Recent advances in self-supervised representation learning have directly driven improvements in anomaly detection. In this position paper, we first explain how self-supervised representations can be easily used to achieve state-of-the-art performance in commonly reported anomaly detection benchmarks. We then argue that tackling the next generation of anomaly detection tasks requires new technical and conceptual improvements in representation learning.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

eliahuhorwitz/3D-ADS pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection (arXiv:2203.05550; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Anomaly Detection and SegmentationAnomaly DetectionRepresentation LearningSelf-Supervised Learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection ODDS kNN AUROC 0.902 #1 of 3 Archive leaderboard report
Anomaly Detection ODDS kNN F1 0.699 #1 of 3 Archive leaderboard report
Anomaly Detection ODDS ICL AUROC 0.889 #2 of 3 Archive leaderboard report
Anomaly Detection ODDS ICL F1 0.681 #2 of 3 Archive leaderboard report
Anomaly Detection ODDS GOAD AUROC 0.782 #3 of 3 Archive leaderboard report
Anomaly Detection ODDS GOAD F1 0.544 #3 of 3 Archive leaderboard report
Anomaly Detection One-class CIFAR-10 DINO-FT AUROC 98.4 #8 of 36 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.

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