Recently introduced generative adversarial networks (GANs) have been shown numerous promising results to generate realistic samples. In the last couple of years, it has been studied to control features in synthetic samples generated by the GAN. Auxiliary classifier GAN (ACGAN), a conventional method to generate conditional samples, employs a classification layer in discriminator to solve the problem. However, in this paper, we demonstrate that the auxiliary classifier can hardly provide good guidance for training of the generator, where the classifier suffers from overfitting. Since the generator learns from classification loss, such a problem has a chance to hinder the training. To overcome this limitation, here, we propose a controllable GAN (ControlGAN) structure. By separating a feature classifier from the discriminator, the classifier can be trained with data augmentation technique, which can support to make a fine classifier. Evaluated with the CIFAR-10 dataset, ControlGAN outperforms AC-WGAN-GP which is an improved version of the ACGAN, where Inception score of the ControlGAN is 8.61 ± 0.10. Furthermore, we demonstrate that the ControlGAN can generate intermediate features and opposite features for interpolated input and extrapolated input labels that are not used in the training process. It implies that the ControlGAN can significantly contribute to the variety of generated samples.
Bibliographical noteFunding Information:
This work was supported by grants from the National Research Foundation of Korea (NRF-2016R1D1A1B03931077), Korea University (K1822271), and Mirae Asset Global Investments as well as a grant from the Institute for Information and Communications Technology Promotion (No.2017-0-00053, A Technology Development of Artificial Intelligence Doctors for Cardiovascular Disease).
© 2019 IEEE.
- Artificial neural network
- generative adversarial networks
- generative model
- sample generation
ASJC Scopus subject areas
- Computer Science(all)
- Materials Science(all)
- Electrical and Electronic Engineering