MultiGenerator Generative Adversarial Nets
This topic contains 0 replies, has 1 voice, and was last updated by arXiv 1 year, 6 months ago.

MultiGenerator Generative Adversarial Nets
We propose in this paper a novel approach to address the mode collapse problem in Generative Adversarial Nets (GANs) by training many generators. The training procedure is formulated as a minimax game among many generators, a classifier, and a discriminator. Generators produce data to fool the discriminator while staying within the decision boundary defined by the classifier as much as possible; classifier estimates the probability that a sample came from each of the generators; and discriminator estimates the probability that a sample came from the training data rather than from all generators. We develop theoretical analysis to show that at equilibrium of this system, the JensenShannon divergence between the equally weighted mixture of all generators’ distributions and the real data distribution is minimal while the JensenShannon divergence among generators’ distributions is maximal. Generators can be trained efficiently by utilizing parameter sharing, thus adding minimal cost to the basic GAN model. We conduct extensive experiments on synthetic and realworld large scale data sets (CIFAR10 and STL10) to evaluate the effectiveness of our proposed method. Experimental results demonstrate the superior performance of our approach in generating diverse and visually appealing samples over the latest stateoftheart GAN’s variants.
MultiGenerator Generative Adversarial Nets
by Quan Hoang, Tu Dinh Nguyen, Trung Le, Dinh Phung
https://arxiv.org/pdf/1708.02556v3.pdf
You must be logged in to reply to this topic.