Wasserstein GAN

By Martín Arjovsky, Soumith Chintala, Soumith Chintala, Léon Bottou, L. Eon Bottou. 2017

5,178 citations recorded by the source corpus.

We introduce a new algorithm named WGAN, an alternative to traditional GAN training. In this new model, we show that we can improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for debugging and hyperparameter searches. Furthermore, we show that the corresponding optimization problem is sound, and provide extensive theoretical work highlighting the deep connections to other distances between distributions.

Subfields: Molecular Biology, Radiology, Nuclear Medicine and Imaging, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

  1. Tommi S. Jaakkola
  2. Regina Barzilay
  3. Song-Chun Zhu
  4. Ying Nian Wu
  5. Qiang Liu
  6. Yilun Du
  7. Stefano Ermon
  8. Igor Mordatch

In Radiology, Nuclear Medicine and Imaging

  1. Bernt Schiele
  2. Zeynep Akata
  3. Han-Jia Ye
  4. De-chuan Zhan
  5. Luc Van Gool
  6. P. Heng
  7. Yongqin Xian
  8. Qi-Yan Dou

In Generative Models

  1. Stefano Ermon
  2. Jun-Yan Zhu
  3. Yoshua Bengio
  4. Richard Zhang
  5. Eli Shechtman
  6. Jiaming Song
  7. Arash Vahdat
  8. Jan Kautz

Citations in the corpus