Training Generative Adversarial Networks (GAN) on high-fidelity images usually requires large-scale GPU-clusters and a vast number of training images. In this paper, we study the few-shot image synthesis task for GAN with minimum computing cost. We propose a light-weight GAN structure that gains superior quality on 1024*1024 resolution. Notably, the model converges from scratch with just a few hours of training on a single RTX-2080 GPU, and has a consistent performance, even with less than 100 training samples. Two technique designs constitute our work, a skip-layer channel-wise excitation module and a self-supervised discriminator trained as a feature-encoder. With thirteen datasets covering a wide variety of image domains (The datasets and code are available at: https://github.com/odegeasslbc/FastGAN-pytorch), we show our model's superior performance compared to the state-of-the-art StyleGAN2, when data and computing budget are limited.

翻译：关于高纤维图像的培训模拟网络(GAN)通常需要大型的GPU-集群和大量培训图像。在本文中,我们研究了GAN的几张短片图像合成任务,其计算成本最低。我们建议了一个在1024*1024分辨率上提高质量的轻量GAN结构。值得注意的是,模型从零开始,仅仅就一个RTX-2080GPU进行了几个小时的培训,而且即使培训样本不到100个,其性能也是一致的。两种技术设计构成了我们的工作,一种是跳板频道的频道引证模块,一种是作为功能编码器受过自我监督的导师的培训。有13套数据集覆盖了广泛的图像领域(数据集和代码见:https://github.com/odegeasslbc/FastGAN-pytorch),当数据和计算预算有限时,我们展示了我们的模型比State-the-art StyGAN2的高级性能。