Faster Projected GAN: Towards Faster Few-Shot Image Generation

TL;DR

This paper introduces Faster Projected GAN, an improved model that reduces training time and memory usage in few-shot image generation by integrating depth separable convolution into the generator.

Contribution

It presents a novel GAN architecture that enhances training efficiency and resource utilization while maintaining image quality, especially in few-shot scenarios.

Findings

20% faster training speed on multiple datasets

15% memory reduction without quality loss

Effective in small sample and specialized scene image generation

Abstract

In order to solve the problems of long training time, large consumption of computing resources and huge parameter amount of GAN network in image generation, this paper proposes an improved GAN network model, which is named Faster Projected GAN, based on Projected GAN. The proposed network is mainly focuses on the improvement of generator of Projected GAN. By introducing depth separable convolution (DSC), the number of parameters of the Projected GAN is reduced, the training speed is accelerated, and memory is saved. Experimental results show that on ffhq-1k, art-painting, Landscape and other few-shot image datasets, a 20% speed increase and a 15% memory saving are achieved. At the same time, FID loss is less or no loss, and the amount of model parameters is better controlled. At the same time, significant training speed improvement has been achieved in the small sample image generation task of special scenes such as earthquake scenes with few public datasets.