Generative Adversarial Nets

Generative Adversarial Networks (GANs) are a framework for training generative models. Two neural networks contest with each other in a zero-sum game framework. A generator network generates candidates (e.g., images) while a discriminator network evaluates them. The generator tries to fool the discriminator, and the discriminator tries to identify the generated images as fake. This adversarial process drives both networks to improve until the generator's output is indistinguishable from real data, leading to powerful generative capabilities that can be used for image enhancement, background removal, and object manipulation.