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

01/12/2021
by   Bingchen Liu, et al.
12

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.

READ FULL TEXT

page 8

page 9

page 16

page 17

page 18

page 19

page 20

page 22

research
09/15/2022

One-Shot Synthesis of Images and Segmentation Masks

Joint synthesis of images and segmentation masks with generative adversa...
research
12/13/2021

DGL-GAN: Discriminator Guided Learning for GAN Compression

Generative Adversarial Networks (GANs) with high computation costs, e.g....
research
11/03/2021

Discriminator Synthesis: On reusing the other half of Generative Adversarial Networks

Generative Adversarial Networks have long since revolutionized the world...
research
06/18/2020

Differentiable Augmentation for Data-Efficient GAN Training

The performance of generative adversarial networks (GANs) heavily deteri...
research
02/28/2021

Ultra-Data-Efficient GAN Training: Drawing A Lottery Ticket First, Then Training It Toughly

Training generative adversarial networks (GANs) with limited data genera...
research
06/09/2022

BigVGAN: A Universal Neural Vocoder with Large-Scale Training

Despite recent progress in generative adversarial network(GAN)-based voc...
research
03/24/2023

Efficient Scale-Invariant Generator with Column-Row Entangled Pixel Synthesis

Any-scale image synthesis offers an efficient and scalable solution to s...

Please sign up or login with your details

Forgot password? Click here to reset