Methods › General › Discriminators › PatchGAN

PatchGAN

516 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

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 ×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 NetworksSee Code · znxlwm/pytorch-pix2pix

Papers archive 2025-07-28

30 shown of 516, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 306 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Translation129
Image-to-Image Translation113
Generative Adversarial Network79
Image Generation60
Domain Adaptation39
Data Augmentation38
SSIM37
Semantic Segmentation37
Segmentation36
Style Transfer32
Diagnostic19
Denoising18
Computed Tomography (CT)16
Object Detection16
object-detection16
Super-Resolution15
Anatomy14
Image Segmentation14
Deep Learning12
Diversity12

Usage over time archive 2025-07-28

Papers per year tagged with PatchGAN: 2016 to 2025, peak 82 82 0 2016: 1 paper 2016 2017: 13 papers 2017 2018: 31 papers 2018 2019: 63 papers 2019 2020: 82 papers 2020 2021: 76 papers 2021 2022: 74 papers 2022 2023: 76 papers 2023 2024: 73 papers 2024 2025: 27 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (516 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Discriminators

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections