Faster Projected GAN: Towards Faster Few-Shot Image Generation

arXiv:2403.08778v1 Announce Type: new
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 …

abstract arxiv computing computing resources consumption cs.cv cs.gr eess.iv faster few-shot gan image image generation network paper resources solve training type