Gated SwitchGAN for multi-domain facial image translation

TL;DR

Gated SwitchGAN introduces an adaptive discriminator and feature-switching for improved multi-domain facial image translation, achieving superior results over existing models like StarGAN, AttGAN, and STGAN.

Contribution

The paper proposes Gated SwitchGAN with a novel feature-switching operation and an adaptive discriminator for more precise multi-domain facial image translation.

Findings

Outperforms StarGAN, AttGAN, and STGAN in visual quality

Achieves higher attribute classification accuracy

Obtains better FID scores on multiple datasets

Abstract

Recent studies on multi-domain facial image translation have achieved impressive results. The existing methods generally provide a discriminator with an auxiliary classifier to impose domain translation. However, these methods neglect important information regarding domain distribution matching. To solve this problem, we propose a switch generative adversarial network (SwitchGAN) with a more adaptive discriminator structure and a matched generator to perform delicate image translation among multiple domains. A feature-switching operation is proposed to achieve feature selection and fusion in our conditional modules. We demonstrate the effectiveness of our model. Furthermore, we also introduce a new capability of our generator that represents attribute intensity control and extracts content information without tailored training. Experiments on the Morph, RaFD and CelebA databases visually and quantitatively show that our extended SwitchGAN (i.e., Gated SwitchGAN) can achieve better translation results than StarGAN, AttGAN and STGAN. The attribute classification accuracy achieved using the trained ResNet-18 model and the FID score obtained using the ImageNet pretrained Inception-v3 model also quantitatively demonstrate the superior performance of our models.