Discriminative-Generative Representation Learning for One-Class Anomaly Detection

TL;DR

This paper introduces a novel self-supervised learning framework that combines generative and discriminative approaches to enhance representation learning for one-class anomaly detection, achieving superior performance and speed.

Contribution

It proposes a discriminative-guided generative model that improves representation learning by leveraging discriminator guidance instead of reconstruction error.

Findings

Outperforms several state-of-the-art methods on benchmark datasets.

Increases performance of GAN-based baseline by 6% on CIFAR-10.

Achieves 2% improvement on MVTAD dataset.

Abstract

As a kind of generative self-supervised learning methods, generative adversarial nets have been widely studied in the field of anomaly detection. However, the representation learning ability of the generator is limited since it pays too much attention to pixel-level details, and generator is difficult to learn abstract semantic representations from label prediction pretext tasks as effective as discriminator. In order to improve the representation learning ability of generator, we propose a self-supervised learning framework combining generative methods and discriminative methods. The generator no longer learns representation by reconstruction error, but the guidance of discriminator, and could benefit from pretext tasks designed for discriminative methods. Our discriminative-generative representation learning method has performance close to discriminative methods and has a great advantage in speed. Our method used in one-class anomaly detection task significantly outperforms several state-of-the-arts on multiple benchmark data sets, increases the performance of the top-performing GAN-based baseline by 6% on CIFAR-10 and 2% on MVTAD.