Anomaly Detection Based on Selection and Weighting in Latent Space

TL;DR

This paper introduces SWAD, a novel autoencoder-based anomaly detection framework that enhances detection by selecting and weighting latent representations, demonstrating superior performance on benchmark and real-world datasets.

Contribution

The paper proposes a new selection-and-weighting approach for latent representations in autoencoders, improving anomaly detection performance.

Findings

SWAD achieves comparable or better results than state-of-the-art methods on benchmark datasets.

SWAD demonstrates effectiveness and superiority on real-world datasets.

The framework enhances anomaly detection by focusing on latent space representations.

Abstract

With the high requirements of automation in the era of Industry 4.0, anomaly detection plays an increasingly important role in higher safety and reliability in the production and manufacturing industry. Recently, autoencoders have been widely used as a backend algorithm for anomaly detection. Different techniques have been developed to improve the anomaly detection performance of autoencoders. Nonetheless, little attention has been paid to the latent representations learned by autoencoders. In this paper, we propose a novel selection-and-weighting-based anomaly detection framework called SWAD. In particular, the learned latent representations are individually selected and weighted. Experiments on both benchmark and real-world datasets have shown the effectiveness and superiority of SWAD. On the benchmark datasets, the SWAD framework has reached comparable or even better performance than the state-of-the-art approaches.