Trendoday

How Far Can Untrained Neural Networks Go in Anomaly Detection? From Tables to Pixels

Anomaly detection (AD) is often framed as a representation-learning problem, where strong performance is expected to require learned features or AD-specific optimization. However, this view can overlo

  • Upvotes6
–Rank now
#22Peak rank
1Days on list
52Score · 7d
Nov 20, 2026First seen
Rank · 7 days

About this paper

Untrained neural networks with fixed random nonlinear features and Mahalanobis scoring can detect anomalies competitively on tabular and visual tasks without weight optimization or pretrained representations.

Anomaly detection (AD) is often framed as a representation-learning problem, where strong performance is expected to require learned features or AD-specific optimization. However, this view can overlook the intrinsic separability of anomalies from normal references, even in the absence of learned representations. We therefore investigate how far untrained neural networks can go in anomaly detection. To this end, we propose PRISM, a framework combining fixed random nonlinear features with normal-reference Mahalanobis scoring for tabular detection and dense visual localization. Across 47 tabular datasets in ADBench, PRISM-T achieves the highest mean AUROC (86.4%) and the second-highest mean…

anomaly detectionrepresentation learninguntrained neural networksfixed random nonlinear featuresMahalanobis scoringtabular anomaly detectiondense visual localizationAUROCAUPRCneural weight optimization
Upvotes
6
Authors
4
Published
Nov 9, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

How Far Can Untrained Neural Networks Go in Anomaly Detection? From Tables to Pixels was first seen on Hugging Face · Daily papers on Nov 20, 2026. Since then it has appeared in 11 checks on 1 different day. Its best position was #22 of 30, reached on Nov 20, 05:29 UTC. It dropped off the list after Nov 20, 23:29 UTC.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 03:2908:2913:2918:2923:29 Nov 20, 03:29 UTC · #25Nov 20, 05:29 UTC · #22Nov 20, 07:29 UTC · #27Nov 20, 09:29 UTC · #27Nov 20, 11:29 UTC · #27Nov 20, 13:29 UTC · #29Nov 20, 15:29 UTC · #26Nov 20, 17:29 UTC · #27Nov 20, 19:29 UTC · #28Nov 20, 21:29 UTC · #28Nov 20, 23:29 UTC · #28

Last 14 days

Best rank per day (UTC).

Nov 9today

Metric history

Platform metric as reported by Hugging Face.

0257 03:2908:2913:2918:2923:29 Nov 20, 03:29 UTC · 6Nov 20, 05:29 UTC · 7Nov 20, 07:29 UTC · 7Nov 20, 09:29 UTC · 7Nov 20, 11:29 UTC · 7Nov 20, 13:29 UTC · 7Nov 20, 15:29 UTC · 7Nov 20, 17:29 UTC · 7Nov 20, 19:29 UTC · 7Nov 20, 21:29 UTC · 7Nov 20, 23:29 UTC · 7

Questions

Is How Far Can Untrained Neural Networks Go in Anomaly Detection? From Tables to Pixels trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 20, 23:29 UTC, after 1 day of trending.

What is the highest rank How Far Can Untrained Neural Networks Go in Anomaly Detection? From Tables to Pixels reached?

#22 on Hugging Face · Daily papers, on Nov 20, 05:29 UTC. Trendoday checks this list every 120 minutes.

How long has How Far Can Untrained Neural Networks Go in Anomaly Detection? From Tables to Pixels been trending?

It was first seen on Nov 20, 2026 and has been on the list on 1 day (11 checks) since.