Weakly-supervised anomaly detection for multimodal data distributions

TL;DR

This paper introduces WVAD, a weakly-supervised anomaly detection method that effectively handles multimodal data by combining a deep variational mixture model with an anomaly scoring mechanism, outperforming existing methods.

Contribution

The paper presents WVAD, a novel weakly-supervised anomaly detection approach designed specifically for multimodal datasets, addressing limitations of prior methods.

Findings

WVAD outperforms existing methods on three real-world datasets.

The deep variational mixture model effectively captures multimodal data features.

WVAD demonstrates robustness in detecting anomalies with minimal labeled data.

Abstract

Weakly-supervised anomaly detection can outperform existing unsupervised methods with the assistance of a very small number of labeled anomalies, which attracts increasing attention from researchers. However, existing weakly-supervised anomaly detection methods are limited as these methods do not factor in the multimodel nature of the real-world data distribution. To mitigate this, we propose the Weakly-supervised Variational-mixture-model-based Anomaly Detector (WVAD). WVAD excels in multimodal datasets. It consists of two components: a deep variational mixture model, and an anomaly score estimator. The deep variational mixture model captures various features of the data from different clusters, then these features are delivered to the anomaly score estimator to assess the anomaly levels. Experimental results on three real-world datasets demonstrate WVAD's superiority.