Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis

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.

PDF Abstract ICLR 2021 PDF ICLR 2021 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Generation ADE-Indoor FastGAN FID 30.33 # 2
Image Generation Pokemon 1024x1024 FastGAN FID 56.46 # 3
Image Generation Pokemon 256x256 FastGAN FID 81.86 # 4

Methods