ICML 2019oral225 citations

A Large-Scale Study on Regularization and Normalization in GANs

Karol Kurach, Mario Lučić, Xiaohua Zhai, Marcin Michalski, Sylvain Gelly

Abstract

Generative adversarial networks (GANs) are a class of deep generative models which aim to learn a target distribution in an unsupervised fashion. While they were successfully applied to many problems, training a GAN is a notoriously challenging task and requires a significant number of hyperparameter tuning, neural architecture engineering, and a non-trivial amount of “tricks". The success in many practical applications coupled with the lack of a measure to quantify the failure modes of GANs resulted in a plethora of proposed losses, regularization and normalization schemes, as well as neural architectures. In this work we take a sober view of the current state of GANs from a practical perspective. We discuss and evaluate common pitfalls and reproducibility issues, open-source our code on Github, and provide pre-trained models on TensorFlow Hub.

BibTeX
@InProceedings{pmlr-v97-kurach19a,
  title = 	 {A Large-Scale Study on Regularization and Normalization in {GAN}s},
  author =       {Kurach, Karol and Lu{\v{c}}i{\'c}, Mario and Zhai, Xiaohua and Michalski, Marcin and Gelly, Sylvain},
  booktitle = 	 {Proceedings of the 36th International Conference on Machine Learning},
  pages = 	 {3581--3590},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
  volume = 	 {97},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {09--15 Jun},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v97/kurach19a/kurach19a.pdf},
  url = 	 {https://proceedings.mlr.press/v97/kurach19a.html},
  abstract = 	 {Generative adversarial networks (GANs) are a class of deep generative models which aim to learn a target distribution in an unsupervised fashion. While they were successfully applied to many problems, training a GAN is a notoriously challenging task and requires a significant number of hyperparameter tuning, neural architecture engineering, and a non-trivial amount of “tricks". The success in many practical applications coupled with the lack of a measure to quantify the failure modes of GANs resulted in a plethora of proposed losses, regularization and normalization schemes, as well as neural architectures. In this work we take a sober view of the current state of GANs from a practical perspective. We discuss and evaluate common pitfalls and reproducibility issues, open-source our code on Github, and provide pre-trained models on TensorFlow Hub.}
}
A Large-Scale Study on Regularization and Normalization in GANs · ICML 2019