Methods › General › Loss Functions › WGAN-GP Loss

WGAN-GP Loss

65 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 Gradient Penalty Loss, or WGAN-GP Loss, is a loss used for generative adversarial networks that augments the Wasserstein loss with a gradient norm penalty for random samples 𝐱̂ ∼ℙ_(𝐱̂) to achieve Lipschitz continuity:

L = 𝔼_(𝐱̂ ∼ℙ_g)[D(𝐱̃)] - 𝔼_(𝐱 ∼ℙᵣ)[D(𝐱)] + λ𝔼_(𝐱̂ ∼ℙ_(𝐱̂))[(||∇_(𝐱̃)D(𝐱̃)||₂-1)²]

It was introduced as part of the WGAN-GP overall model.

PaperSourceSee Code · eriklindernoren/PyTorch-GAN

Papers archive 2025-07-28

30 shown of 65, 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 85 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
Generative Adversarial Network15
Image Generation13
Text to Speech9
text-to-speech9
Data Augmentation4
Speech Synthesis4
Translation4
Vocal Bursts Intensity Prediction4
Disentanglement3
Diversity3
Synthetic Data Generation3
Voice Conversion3
Attribute2
Audio Generation2
CPU2
Conditional Image Generation2
Decoder2
Face Generation2
GPU2
Image-to-Image Translation2

Usage over time archive 2025-07-28

Papers per year tagged with WGAN-GP Loss: 2017 to 2025, peak 14 14 0 2017: 4 papers 2017 2018: 6 papers 2018 2019: 7 papers 2019 2020: 14 papers 2020 2021: 13 papers 2021 2022: 9 papers 2022 2023: 3 papers 2023 2024: 7 papers 2024 2025: 2 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (65 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

Loss Functions

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