SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.00339 · ICML · 2020

Rethinking Assumptions in Deep Anomaly Detection

Lukas Ruff, Robert Vandermeulen, Billy Franks, Marius Kloft, T Berlin, T Kaiser- Slautern, Germany

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Though anomaly detection (AD) can be viewed as a classification problem (nominal vs. anomalous) it is usually treated in an unsupervised manner since one typically does not have access to, or it is infeasible to utilize, a dataset that sufficiently characterizes what it means to be "anomalous." In this paper we present results demonstrating that this intuition surprisingly seems not to extend to deep AD on images. For a recent AD benchmark on ImageNet, classifiers trained to discern between normal samples and just a few (64) random natural images are able to outperform the current state of the art in deep AD. Experimentally we discover that the multiscale structure of image data makes example anomalies exceptionally informative.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2006.00339")
get_code_for_paper("2006.00339")
have("2006.00339")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2006.00339.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2006.00339.svg)](https://syntology.ai/paper/2006.00339)

Connect an agent — have() is free.