Generative Adversarial Nets

Generative Adversarial Networks (GANs) are a framework for estimating generative models via an adversarial process, where 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 training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. GANs have shown promise in image generation, image-to-image translation, and other applications.