Anomaly Detection Based on Multiple-Hypothesis Autoencoder

TL;DR

This paper introduces a Multiple-hypothesis Autoencoder (MH-AE) with multiple decoders to enhance anomaly detection by expanding the restoration area, leading to improved performance over traditional autoencoders.

Contribution

The paper proposes a novel MH-AE model with multiple decoders to address the limited restoration area in traditional autoencoders for anomaly detection.

Findings

MH-AE improves anomaly detection accuracy.

The model outperforms traditional autoencoders on various datasets.

Decentralized decoders increase the restoration area.

Abstract

Recently Autoencoder(AE) based models are widely used in the field of anomaly detection. A model trained with normal data generates a larger restoration error for abnormal data. Whether or not abnormal data is determined by observing the restoration error. It takes a lot of cost and time to obtain abnormal data in the industrial field. Therefore the model trains only normal data and detects abnormal data in the inference phase. However, the restoration area for the input data of AE is limited in the latent space. To solve this problem, we propose Multiple-hypothesis Autoencoder(MH-AE) model composed of several decoders. MH-AE model increases the restoration area through contention between decoders. The proposed method shows that the anomaly detection performance is improved compared to the traditional AE for various input datasets.