Generative Adversarial Nets

This paper introduces a new framework for estimating generative models via an adversarial process, in which two models are trained simultaneously: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The generative model can be thought of as a counterfeiter trying to produce fake currency and the discriminative model as police trying to detect the fake currency. Competition drives both teams to improve their methods until the counterfeits are indistinguishable from the genuine articles.