Corpus ID: 49305856

Banach Wasserstein GAN

@inproceedings{Adler2018BanachWG,
  title={Banach Wasserstein GAN},
  author={Jonas Adler and S. Lunz},
  booktitle={NeurIPS},
  year={2018}
}
  • Jonas Adler, S. Lunz
  • Published in NeurIPS 2018
  • Computer Science, Mathematics
  • Wasserstein Generative Adversarial Networks (WGANs) can be used to generate realistic samples from complicated image distributions. [...] Key Method We generalize the theory of WGAN with gradient penalty to Banach spaces, allowing practitioners to select the features to emphasize in the generator. We further discuss the effect of some particular choices of underlying norms, focusing on Sobolev norms. Finally, we demonstrate the impact of the choice of norm on model performance and show state-of-the-art…Expand Abstract
    56 Citations

    Figures and Topics from this paper

    Wasserstein Proximal of GANs
    • 15
    • PDF
    Orthogonal Wasserstein GANs
    • 1
    • PDF
    Virtual Adversarial Lipschitz Regularization
    • 5
    • Highly Influenced
    • PDF
    Adversarial Lipschitz Regularization
    • 9
    • Highly Influenced
    A Wasserstein GAN model with the total variational regularization
    • 1
    • PDF
    Sliced Wasserstein Generative Models
    • J. Wu, Z. Huang, +4 authors L. Gool
    • Computer Science
    • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2019
    • 44
    • Highly Influenced
    • PDF
    Improved Procedures for Training Primal Wasserstein GANs
    • T. Zhang, Zhongnian Li, Qi Zhu, Daoqiang Zhang
    • Computer Science
    • 2019 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI)
    • 2019
    A Comparative Assessment of the Impact of Various Norms on Wasserstein Generative Adversarial Networks
    Lipschitz Generative Adversarial Nets
    • 32
    • PDF
    Sobolev Wasserstein GAN

    References

    SHOWING 1-10 OF 22 REFERENCES
    Improved Training of Wasserstein GANs
    • 3,935
    • Highly Influential
    • PDF
    On the regularization of Wasserstein GANs
    • 102
    • PDF
    Wasserstein Generative Adversarial Networks
    • 2,355
    • Highly Influential
    • PDF
    Least Squares Generative Adversarial Networks
    • 1,867
    • PDF
    GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
    • 2,361
    • PDF
    Energy-based Generative Adversarial Network
    • 745
    • PDF
    Approximation and Convergence Properties of Generative Adversarial Learning
    • 85
    • PDF
    Spectral Normalization for Generative Adversarial Networks
    • 1,757
    • PDF