ViTGAN: Training GANs with Vision Transformers

Recently, Vision Transformers (ViTs) have shown competitive performance on image recognition while requiring less vision-specific inductive biases. In this paper, we investigate if such performance can be extended to image generation. To this end, we integrate the ViT architecture into generative adversarial networks (GANs). For ViT discriminators, we observe that existing regularization methods for GANs interact poorly with self-attention, causing serious instability during training. To resolve this issue, we introduce several novel regularization techniques for training GANs with ViTs. For ViT generators, we examine architectural choices for latent and pixel mapping layers to facilitate convergence. Empirically, our approach, named ViTGAN, achieves comparable performance to the leading CNNbased GAN models on three datasets: CIFAR-10, CelebA, and LSUN bedroom. Convolutional neural networks (CNNs) (LeCun et al., 1989) are dominating computer vision today, thanks to their powerful capability of convolution (weight-sharing and local-connectivity) and pooling (translation equivariance). Recently, however, Transformer architectures (Vaswani et al., 2017) have started to rival CNNs in many vision tasks. In particular, Vision Transformers (ViTs) (Dosovitskiy et al., 2021), which interpret an image as a sequence of tokens (analogous to words in natural language), have been shown to achieve comparable classification accuracy with smaller computational budgets (i.e., fewer FLOPs) on the ImageNet benchmark. Unlike CNNs, ViTs capture a different inductive bias through self-attention where each patch is attended to all patches of the same image. ViTs, along with their variants (Touvron et al., 2020; Tolstikhin et al., 2021), though still in their infancy, have demonstrated advantages in modeling non-local contextual dependencies (Ranftl et al., 2021; Strudel et al., 2021) as well as promising efficiency and scalability.