# Representation Learning in Anomaly Detection: Successes, Limits and a Grand Challenge

Source: [Representation Learning in Anomaly Detection: Successes, Limits and a Grand Challenge](<https://www.sota2.com/research/paper/68fa70181e209131cea48f25>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:33:16.495Z

Authors: Yedid Hoshen

Published: 2023-07-20T17:59:11.000Z

## Abstract

In this perspective paper, we argue that the dominant paradigm in anomaly detection cannot scale indefinitely and will eventually hit fundamental limits. This is due to the a no free lunch principle for anomaly detection. These limitations can be overcome when there are strong tasks priors, as is the case for many industrial tasks. When such priors do not exists, the task is much harder for anomaly detection. We pose two such tasks as grand challenges for anomaly detection: i) scientific discovery by anomaly detection ii) a "mini-grand" challenge of detecting the most anomalous image in the ImageNet dataset. We believe new anomaly detection tools and ideas would need to be developed to overcome these challenges.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2307.11085>)

[PDF](<https://arxiv.org/pdf/2307.11085.pdf>)