Styleformer: Transformer based Generative Adversarial Networks with Style Vector

Abstract

We propose Styleformer, which is a style-based generator for GAN architecture, but a convolution-free transformer-based generator. In our paper, we explain how a transformer can generate high-quality images, overcoming the disadvantage that convolution operations are difficult to capture global features in an image. Furthermore, we change the demodulation of StyleGAN2 and modify the existing transformer structure (e.g., residual connection, layer normalization) to create a strong style-based generator with a convolution-free structure. We also make Styleformer lighter by applying Linformer, enabling Styleformer to generate higher resolution images and result in improvements in terms of speed and memory. We experiment with the low-resolution image dataset such as CIFAR-10, as well as the high-resolution image dataset like LSUN-church. Styleformer records FID 2.82 and IS 9.94 on CIFAR-10, a benchmark dataset, which is comparable performance to the current state-of-the-art and outperforms all GAN-based generative models, including StyleGAN2-ADA with fewer parameters on the unconditional setting. We also both achieve new state-of-the-art with FID 15.17, IS 11.01, and FID 3.66, respectively on STL-10 and CelebA. We release our code at https://github.com/Jeeseung-Park/Styleformer.

CVPR 2022

References in corpus (10)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Is Space-Time Attention All You Need for Video Understanding?
• MLP-Mixer: An all-MLP Architecture for Vision
• Linformer: Self-Attention with Linear Complexity
• A Learned Representation For Artistic Style
• CvT: Introducing Convolutions to Vision Transformers
• LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
• Generative Adversarial Transformers
• MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis

Cited by in corpus (3)

• GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks
• Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory
• Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?