Deep Generative Model using Unregularized Score for Anomaly Detection with Heterogeneous Complexity

TL;DR

This paper introduces an unregularized scoring method for deep generative models that improves anomaly detection in images with heterogeneous complexity by reducing the influence of regularization on likelihood estimates.

Contribution

The authors propose removing regularization terms from deep generative models to create a more robust anomaly score for images with varying complexity.

Findings

Unregularized score is more robust to sample complexity.

Improved anomaly detection performance on manufacturing datasets.

Regularization influences likelihoods based on sample complexity.

Abstract

Accurate and automated detection of anomalous samples in a natural image dataset can be accomplished with a probabilistic model for end-to-end modeling of images. Such images have heterogeneous complexity, however, and a probabilistic model overlooks simply shaped objects with small anomalies. This is because the probabilistic model assigns undesirably lower likelihoods to complexly shaped objects that are nevertheless consistent with set standards. To overcome this difficulty, we propose an unregularized score for deep generative models (DGMs), which are generative models leveraging deep neural networks. We found that the regularization terms of the DGMs considerably influence the anomaly score depending on the complexity of the samples. By removing these terms, we obtain an unregularized score, which we evaluated on a toy dataset and real-world manufacturing datasets. Empirical results demonstrate that the unregularized score is robust to the inherent complexity of samples and can be used to better detect anomalies.