PatchGAN

Introduced by Isola et al. in Image-to-Image Translation with Conditional Adversarial Networks

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 $N \times N$ 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 $D$. 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.

Source: Image-to-Image Translation with Conditional Adversarial Networks

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Translation	118	14.57%
Image-to-Image Translation	101	12.47%
Image Generation	50	6.17%
Domain Adaptation	33	4.07%
Semantic Segmentation	28	3.46%
Style Transfer	27	3.33%
Super-Resolution	14	1.73%
Denoising	13	1.60%
Object Detection	11	1.36%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
🤖 No Components Found	You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories

Add Remove

Discriminators