Reimagining Anomalies: What If Anomalies Were Normal?
This addresses the challenge of interpretability in anomaly detection for users, though it is incremental as it builds on existing anomaly detectors.
The paper tackles the problem of explaining why deep learning-based anomaly detectors classify instances as anomalous by introducing a method that generates multiple counterfactual examples to provide high-level semantic explanations, showing it can achieve high-quality explanations across various image datasets.
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 counterfactual examples for each anomaly, capturing diverse concepts of anomalousness. A counterfactual example is a modification of the anomaly that is perceived as normal by the anomaly detector. The method provides a high-level semantic explanation of the mechanism that triggered the anomaly detector, allowing users to explore "what-if scenarios." Qualitative and quantitative analyses across various image datasets show that the method applied to state-of-the-art anomaly detectors can achieve high-quality semantic explanations of detectors.