Styleformer: Transformer based Generative Adversarial Networks with Style Vector
Authors:
Preprint
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.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows2021
- CvT: Introducing Convolutions to Vision Transformers2021
- LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference2021
- Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers2021
- Analyzing and Improving the Image Quality of StyleGAN2020
- AdversarialNAS: Adversarial Neural Architecture Search for GANs2020
- AutoGAN: Neural Architecture Search for Generative Adversarial Networks2019
- Escaping from Collapsing Modes in a Constrained Space2018
- On the Effectiveness of Least Squares Generative Adversarial NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization2017