Stabilizing Adversarially Learned One-Class Novelty Detection Using Pseudo Anomalies
This addresses the problem of training instability in anomaly detection for researchers and practitioners, offering a more robust framework, though it is incremental as it builds on existing adversarial methods.
The paper tackles the instability in adversarially learned one-class novelty detection by transforming the discriminator's role to distinguish good vs. bad quality reconstructions, using pseudo anomalies from generator states, and achieves excellent performance across six datasets in domains like image/video anomaly detection, medical diagnosis, and network security.
Recently, anomaly scores have been formulated using reconstruction loss of the adversarially learned generators and/or classification loss of discriminators. Unavailability of anomaly examples in the training data makes optimization of such networks challenging. Attributed to the adversarial training, performance of such models fluctuates drastically with each training step, making it difficult to halt the training at an optimal point. In the current study, we propose a robust anomaly detection framework that overcomes such instability by transforming the fundamental role of the discriminator from identifying real vs. fake data to distinguishing good vs. bad quality reconstructions. For this purpose, we propose a method that utilizes the current state as well as an old state of the same generator to create good and bad quality reconstruction examples. The discriminator is trained on these examples to detect the subtle distortions that are often present in the reconstructions of anomalous data. In addition, we propose an efficient generic criterion to stop the training of our model, ensuring elevated performance. Extensive experiments performed on six datasets across multiple domains including image and video based anomaly detection, medical diagnosis, and network security, have demonstrated excellent performance of our approach.