Dual-encoder Bidirectional Generative Adversarial Networks for Anomaly Detection
This work is significant for researchers and practitioners using GAN-based models for anomaly detection, particularly in domains like medical imaging, by addressing a known limitation in their ability to distinguish anomalies.
This paper tackles the problem of bad cycle consistency in bidirectional GANs for anomaly detection, where the model struggles to reproduce samples with significant differences between normal and abnormal data. The proposed dual-encoder bidirectional GAN aims to mitigate this by better preserving sample information, leading to improved anomaly detection.
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.