Dual-encoder Bidirectional Generative Adversarial Networks for Anomaly Detection

TL;DR

This paper introduces a dual-encoder bidirectional GAN architecture that enhances anomaly detection by improving cycle consistency and better capturing normal data distributions, demonstrated on MRI datasets.

Contribution

The proposed dual-encoder bidirectional GAN reduces bad cycle consistency, leading to improved anomaly detection performance over traditional GAN models.

Findings

Enhanced anomaly detection accuracy on benchmark datasets

Effective in MRI brain anomaly detection

Reduces issues with large differences between normal and abnormal samples

Abstract

Generative adversarial networks (GANs) have shown promise for various problems including anomaly detection. When anomaly detection is performed using GAN models that learn only the features of normal data samples, data that are not similar to normal data are detected as abnormal samples. The present approach is developed by employing a dual-encoder in a bidirectional GAN architecture that is trained simultaneously with a generator and a discriminator network. Through the learning mechanism, the proposed method aims to reduce the problem of bad cycle consistency, in which a bidirectional GAN might not be able to reproduce samples with a large difference between normal and abnormal samples. We assume that bad cycle consistency occurs when the method does not preserve enough information of the sample data. We show that our proposed method performs well in capturing the distribution of normal samples, thereby improving anomaly detection on GAN-based models. Experiments are reported in which our method is applied to publicly available datasets, including application to a brain magnetic resonance imaging anomaly detection system.