Creating Ensembles of Generative Adversarial Network Discriminators for One-Class Classification

Tools

Ermaliuc, Miha; Stamate, Daniel; Magoulas, George D. and Pu, Ida. 2021. 'Creating Ensembles of Generative Adversarial Network Discriminators for One-Class Classification'. In: International Conference on Engineering Applications of Neural Networks. Halkidiki, Greece 25–27 June 2021. [Conference or Workshop Item]

Preview

Text
GANOCC_EANN21.v1.7.pdf - Accepted Version
Download (382kB) | Preview

Official URL: https://doi.org/10.1007/978-3-030-80568-5_2

Abstract or Description

We introduce an algorithm for one-class classification based on binary classification of the target class against synthetic samples. We use a process inspired by Generative Adversarial Networks (GANs) in order to both acquire synthetic samples and to build the one-class classifier. The first objective is achieved by leading the generator’s output into close vicinities of the target class region. For the second objective, we obtain a one-class classifier by generating an ensemble of discriminators obtained from the GAN’s training process. Our approach is tested on publicly available datasets producing promising results when compared to other methods.

Item Type:

Conference or Workshop Item (Paper)

Identification Number (DOI):

https://doi.org/10.1007/978-3-030-80568-5_2