Discriminative-Generative Representation Learning for One-Class Anomaly Detection
arXiv:2107.12753
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.
arXiv commente.g.:13 pages, 6 figures
References in corpus (9)
- Spectral Normalization for Generative Adversarial Networks
- Instance Normalization: The Missing Ingredient for Fast Stylization
- Adversarial Feature Learning
- Adversarially Learned Inference
- Efficient GAN-Based Anomaly Detection
- Deep Anomaly Detection Using Geometric Transformations
- CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
- Classification-Based Anomaly Detection for General Data
- Controllable Invariance through Adversarial Feature Learning