Auto-encoder generative adversarial networks

Issue title: Special Section: Applications of intelligent & fuzzy theory in engineering technologies and applied science

Guest editors: Stanley Lima and Álvaro Rocha

Article type: Research Article

Authors: Zhai, Zhonghua^{; *}

Affiliations: School of Mathematical Sciences, Zhejiang University, China

Correspondence: [*] Corresponding author. Zhonghua Zhai, School of Mathematical Sciences, Zhejiang University, China. E-mail: huangzyone@163.com.

Abstract: Generative Adversarial Networks have demonstrated potential on a variety of generative tasks, although they are regarded as unstable and sometimes they miss modes. We propose Auto-encoder Generative Adversarial Networks - a convolutional neural network combining auto-encoders with Generative Adversarial Networks. The former brings more information to Generative Adversarial Networks to reduce problems of miss modes and the latter makes the picture generated more coherent because it can better handle multiple modes in the output. We also show that image composition is available for Auto-encoder Generative Adversarial Networks so that it can be used for many feature-based tasks. Besides, we can generate different samples by adding a random noise to a feature vector.

Keywords: Generative adversarial networks, auto encoder, joint loss, image composition

DOI: 10.3233/JIFS-169659

Journal: Journal of Intelligent & Fuzzy Systems, vol. 35, no. 3, pp. 3043-3049, 2018