ML Anthology

McGan: Mean and Covariance Feature Matching GAN

Youssef Mroueh, Tom Sercu, Vaibhava Goel
ICML 2017 pp. 2527-2535
/icml/2017/mroueh2017icml-mcgan/

Abstract

We introduce new families of Integral Probability Metrics (IPM) for training Generative Adversarial Networks (GAN). Our IPMs are based on matching statistics of distributions embedded in a finite dimensional feature space. Mean and covariance feature matching IPMs allow for stable training of GANs, which we will call McGan. McGan minimizes a meaningful loss between distributions.

PDF ICML Semantic Scholar

Cite

Text

Mroueh et al. "McGan: Mean and Covariance Feature Matching GAN." International Conference on Machine Learning, 2017.

Markdown

[Mroueh et al. "McGan: Mean and Covariance Feature Matching GAN." International Conference on Machine Learning, 2017.](https://mlanthology.org/icml/2017/mroueh2017icml-mcgan/)

BibTeX

@inproceedings{mroueh2017icml-mcgan,
  title     = {{McGan: Mean and Covariance Feature Matching GAN}},
  author    = {Mroueh, Youssef and Sercu, Tom and Goel, Vaibhava},
  booktitle = {International Conference on Machine Learning},
  year      = {2017},
  pages     = {2527-2535},
  volume    = {70},
  url       = {https://mlanthology.org/icml/2017/mroueh2017icml-mcgan/}
}