Corpus ID: 208512753

AuthorGAN: Improving GAN Reproducibility using a Modular GAN Framework

@article{Sinha2019AuthorGANIG,
  title={AuthorGAN: Improving GAN Reproducibility using a Modular GAN Framework},
  author={Raunak Sinha and A. Sankaran and Mayank Vatsa and R. Singh},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.13250}
}
Generative models are becoming increasingly popular in the literature, with Generative Adversarial Networks (GAN) being the most successful variant, yet. With this increasing demand and popularity, it is becoming equally difficult and challenging to implement and consume GAN models. A qualitative user survey conducted across 47 practitioners show that expert level skill is required to use GAN model for a given task, despite the presence of various open source libraries. In this research, we… Expand

References

SHOWING 1-10 OF 15 REFERENCES
Improved Training of Wasserstein GANs
  • 4,216
  • PDF
Progressive Growing of GANs for Improved Quality, Stability, and Variation
  • 2,729
  • PDF
NIPS 2016 Tutorial: Generative Adversarial Networks
  • 900
  • PDF
Generative Adversarial Nets
  • 22,230
  • PDF
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
  • 7,822
  • PDF
A Practical Guide to Training Restricted Boltzmann Machines
  • 2,444
  • PDF
Latent Dirichlet Allocation
  • 26,722
  • PDF
Wasserstein GAN
  • 2,285
  • PDF
Information processing in dynamical systems: foundations of harmony theory
  • 1,835
  • PDF
A Hidden Markov Model for Predicting Transmembrane Helices in Protein Sequences
  • 2,301
  • PDF
...
1
2
...