Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN)

Autor:	Bazrafkan, Shabab, Javidnia, Hossein, Corcoran, Peter
Rok vydání:	2018
Předmět:	Electrical Engineering and Systems Science - Image and Video Processing Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning
Druh dokumentu:	Working Paper
Popis:	One of the most interesting challenges in Artificial Intelligence is to train conditional generators which are able to provide labeled adversarial samples drawn from a specific distribution. In this work, a new framework is presented to train a deep conditional generator by placing a classifier in parallel with the discriminator and back propagate the classification error through the generator network. The method is versatile and is applicable to any variations of Generative Adversarial Network (GAN) implementation, and also gives superior results compared to similar methods. Comment: This paper will be uploaded as two separate manuscripts
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1805.00316 Zobrazit plný text záznamu View this record from Arxiv