Flooding Regularization for Stable Training of Generative Adversarial Networks

arXiv:2311.00318v2 Announce Type: replace
Abstract: Generative Adversarial Networks (GANs) have shown remarkable performance in image generation. However, GAN training suffers from the problem of instability. One of the main approaches to address this problem is to modify the loss function, often using regularization terms in addition to changing the type of adversarial losses. This paper focuses on directly regularizing the adversarial loss function. We propose a method that applies flooding, an overfitting suppression method in supervised learning, to GANs to …

abstract adversarial arxiv cs.cv cs.lg flooding function gan gans generative generative adversarial networks however image image generation loss networks performance regularization terms training type