SuperstarGAN: Generative adversarial networks for image-to-image translation in large-scale domains

Abstract

Image-to-image translation with generative adversarial networks (GANs) has been extensively studied in recent years. Among the models, StarGAN has achieved image-to-image translation for multiple domains with a single generator, whereas conventional models require multiple generators. However, StarGAN has several limitations, including the lack of capacity to learn mappings among large-scale domains; furthermore, StarGAN can barely express small feature changes. To address the limitations, we propose an improved StarGAN, namely SuperstarGAN. We adopted the idea, first proposed in controllable GAN (ControlGAN), of training an independent classifier with the data augmentation techniques to handle the overfitting problem in the classification of StarGAN structures. Since the generator with a well-trained classifier can express small features belonging to the target domain, SuperstarGAN achieves image-to-image translation in large-scale domains. Evaluated with a face image dataset, SuperstarGAN demonstrated improved performance in terms of Fréchet Inception distance (FID) and learned perceptual image patch similarity (LPIPS). Specifically, compared to StarGAN, SuperstarGAN exhibited decreased FID and LPIPS by 18.1% and 42.5%, respectively. Furthermore, we conducted an additional experiment with interpolated and extrapolated label values, indicating the ability of SuperstarGAN to control the degree of expression of the target domain features in generated images. Additionally, SuperstarGAN was successfully adapted to an animal face dataset and a painting dataset, where it can translate styles of animal faces (i.e., a cat to a tiger) and styles of painters (i.e., Hassam to Picasso), respectively, which explains the generality of SuperstarGAN regardless of datasets.