Toward Faithful Explanations in Acoustic Anomaly Detection

TL;DR

This paper compares autoencoder and mask autoencoder models for audio anomaly detection, demonstrating that masked training enhances interpretability and faithfulness of explanations without sacrificing detection accuracy.

Contribution

It introduces a perturbation-based faithfulness metric and shows that masked autoencoders provide more accurate and temporally precise explanations in industrial audio anomaly detection.

Findings

Masked autoencoders offer more faithful explanations.

Incorporating interpretability improves anomaly detection pipelines.

Masked training does not reduce detection performance.

Abstract

Interpretability is essential for user trust in real-world anomaly detection applications. However, deep learning models, despite their strong performance, often lack transparency. In this work, we study the interpretability of autoencoder-based models for audio anomaly detection, by comparing a standard autoencoder (AE) with a mask autoencoder (MAE) in terms of detection performance and interpretability. We applied several attribution methods, including error maps, saliency maps, SmoothGrad, Integrated Gradients, GradSHAP, and Grad-CAM. Although MAE shows a slightly lower detection, it consistently provides more faithful and temporally precise explanations, suggesting a better alignment with true anomalies. To assess the relevance of the regions highlighted by the explanation method, we propose a perturbation-based faithfulness metric that replaces them with their reconstructions to simulate normal input. Our findings, based on experiments in a real industrial scenario, highlight the importance of incorporating interpretability into anomaly detection pipelines and show that masked training improves explanation quality without compromising performance.