Methods › Computer Vision › Generative Adversarial Networks › WGAN GP

Wasserstein GAN (Gradient Penalty)

WGAN GP

11 papers tagged archive 2025-07-28

Introduced by Ishaan Gulrajani et al. in Improved Training of Wasserstein GANs

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

Wasserstein GAN + Gradient Penalty, or WGAN-GP, is a generative adversarial network that uses the Wasserstein loss formulation plus a gradient norm penalty to achieve Lipschitz continuity.

The original WGAN uses weight clipping to achieve 1-Lipschitz functions, but this can lead to undesirable behaviour by creating pathological value surfaces and capacity underuse, as well as gradient explosion/vanishing without careful tuning of the weight clipping parameter c.

A Gradient Penalty is a soft version of the Lipschitz constraint, which follows from the fact that functions are 1-Lipschitz iff the gradients are of norm at most 1 everywhere. The squared difference from norm 1 is used as the gradient penalty.

PaperSourceSee Code · eriklindernoren/PyTorch-GAN

Papers archive 2025-07-28

11 shown of 11, 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 26 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
Image Generation3
Diversity2
Generative Adversarial Network2
Class Incremental Learning1
Conditional Image Generation1
Continual Learning1
Data Augmentation1
Decision Making1
Disentanglement1
Emotion Recognition in Conversation1
Exposure Fairness1
Fairness1
General Classification1
Hippocampus1
Image Classification1
Image Super-Resolution1
Language Modeling1
Language Modelling1
Music Generation1
Recommendation Systems1

Usage over time archive 2025-07-28

Papers per year tagged with WGAN GP: 2017 to 2022, peak 3 3 0 2017: 3 papers 2017 2018: 2 papers 2018 2019: 2 papers 2019 2020: 2 papers 2020 2021: 1 paper 2021 2022: 1 paper 2022
Papers per year the archive tags with this method, by the paper's archive date (11 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

Generative Adversarial Networks

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