Reimagining Anomalies: What If Anomalies Were Normal?

TL;DR

This paper presents a novel explanation method for image anomaly detection that generates multiple alternative normal-like modifications for each anomaly, enabling better understanding of the detector's decision process.

Contribution

It introduces a new explanation approach that captures diverse concepts of anomalousness and offers semantic insights into the detection mechanism.

Findings

High-quality semantic explanations achieved on various datasets.

Method effectively generates multiple normal-like modifications for anomalies.

Enhances interpretability of state-of-the-art anomaly detectors.

Abstract

Deep learning-based methods have achieved a breakthrough in image anomaly detection, but their complexity introduces a considerable challenge to understanding why an instance is predicted to be anomalous. We introduce a novel explanation method that generates multiple alternative modifications for each anomaly, capturing diverse concepts of anomalousness. Each modification is trained to be perceived as normal by the anomaly detector. The method provides a semantic explanation of the mechanism that triggered the detector, allowing users to explore ``what-if scenarios.'' Qualitative and quantitative analyses across various image datasets demonstrate that applying this method to state-of-the-art detectors provides high-quality semantic explanations.