ALGAN: Anomaly Detection by Generating Pseudo Anomalous Data via Latent Variables
This addresses the problem of limited anomalous data in anomaly detection tasks, offering a faster solution, but it is incremental as it builds on existing GAN approaches.
The paper tackled anomaly detection with scarce anomalous data by proposing ALGAN, a GAN-based method that generates pseudo-anomalous data from normal data using latent variables, achieving AUROC comparable to state-of-the-art methods with much faster prediction time.
In many anomaly detection tasks, where anomalous data rarely appear and are difficult to collect, training using only normal data is important. Although it is possible to manually create anomalous data using prior knowledge, they may be subject to user bias. In this paper, we propose an Anomalous Latent variable Generative Adversarial Network (ALGAN) in which the GAN generator produces pseudo-anomalous data as well as fake-normal data, whereas the discriminator is trained to distinguish between normal and pseudo-anomalous data. This differs from the standard GAN discriminator, which specializes in classifying two similar classes. The training dataset contains only normal data; the latent variables are introduced in anomalous states and are input into the generator to produce diverse pseudo-anomalous data. We compared the performance of ALGAN with other existing methods on the MVTec-AD, Magnetic Tile Defects, and COIL-100 datasets. The experimental results showed that ALGAN exhibited an AUROC comparable to those of state-of-the-art methods while achieving a much faster prediction time.