Viet-Anh on Software Logo

What is: PatchGAN?

SourceImage-to-Image Translation with Conditional Adversarial Networks
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

PatchGAN is a type of discriminator for generative adversarial networks which only penalizes structure at the scale of local image patches. The PatchGAN discriminator tries to classify if each N×NN \times N patch in an image is real or fake. This discriminator is run convolutionally across the image, averaging all responses to provide the ultimate output of DD. Such a discriminator effectively models the image as a Markov random field, assuming independence between pixels separated by more than a patch diameter. It can be understood as a type of texture/style loss.