Recognition: unknown
Improved Training of Wasserstein GANs
read the original abstract
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge. We find that these problems are often due to the use of weight clipping in WGAN to enforce a Lipschitz constraint on the critic, which can lead to undesired behavior. We propose an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input. Our proposed method performs better than standard WGAN and enables stable training of a wide variety of GAN architectures with almost no hyperparameter tuning, including 101-layer ResNets and language models over discrete data. We also achieve high quality generations on CIFAR-10 and LSUN bedrooms.
This paper has not been read by Pith yet.
Forward citations
Cited by 7 Pith papers
-
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Progressive growing stabilizes GAN training to produce high-resolution images of unprecedented quality and achieves a record unsupervised inception score of 8.80 on CIFAR10.
-
Separate Universe Super-Resolution Emulator
A generative adversarial network emulator upscales low-resolution N-body simulations with non-zero curvature to high resolution, recovering most large-scale power but with up to 10% small-scale suppression and altered...
-
Ensemble Distributionally Robust Bayesian Optimisation
A tractable ensemble distributionally robust Bayesian optimization method achieves improved sublinear regret bounds under context uncertainty.
-
Fast Voxelization and Level of Detail for Microgeometry Rendering
A CUDA-parallel voxelizer and hierarchical SGGX clustering representation enable faster, more accurate level-of-detail rendering of sparse microgeometry volumes.
-
Demystifying MMD GANs
MMD GANs have unbiased critic gradients but biased generator gradients from sample-based learning, and the Kernel Inception Distance provides a practical new measure for GAN convergence and dynamic learning rate adaptation.
-
On the Tradeoffs of On-Device Generative Models in Federated Predictive Maintenance Systems
Experiments on real industrial time series show that partial model sharing improves diffusion model performance in bandwidth-limited non-IID settings, while full sharing stabilizes GAN training but offers less robustn...
-
Conditional Wasserstein GAN for Simulating Neutrino Event Summaries using Incident Energy of Electron Neutrinos
A conditional Wasserstein GAN generates complete kinematic event summaries for IBD-CC, NC, and NuEElastic electron neutrino interactions that match GENIE distributions in 1D marginals and correlations.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.