Least Squares Generative Adversarial Networks

@article{Mao2017LeastSG,
  title={Least Squares Generative Adversarial Networks},
  author={Xudong Mao and Qing Li and Haoran Xie and Raymond Y. K. Lau and Zhen Wang and Stephen Paul Smolley},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={2813-2821}
}
Unsupervised learning with generative adversarial networks (GANs) has proven hugely successful. Regular GANs hypothesize the discriminator as a classifier with the sigmoid cross entropy loss function. However, we found that this loss function may lead to the vanishing gradients problem during the learning process. To overcome such a problem, we propose in this paper the Least Squares Generative Adversarial Networks (LSGANs) which adopt the least squares loss function for the discriminator. We… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 468 CITATIONS, ESTIMATED 83% COVERAGE

Gated2Depth: Real-time Dense Lidar from Gated Images

VIEW 7 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Data Hallucination , Falsification and Validation using Generative Models and Formal Methods by

José Rafael Valle Gomes da Costa
  • 2018
VIEW 11 EXCERPTS
CITES RESULTS, BACKGROUND & METHODS
HIGHLY INFLUENCED

GANs beyond divergence minimization

VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Generative Adversarial Style Transfer Networks for Face Aging

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2018
VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2017
2019

CITATION STATISTICS

  • 78 Highly Influenced Citations

  • Averaged 173 Citations per year over the last 3 years

  • 68% Increase in citations per year in 2018 over 2017

References

Publications referenced by this paper.
SHOWING 1-10 OF 34 REFERENCES

Wasserstein GAN

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Auto-Encoding Variational Bayes

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Generative Adversarial Nets

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Lecture 6.5—RMSProp: Divide the gradient by a running average of its recent magnitude

T. Tieleman, G. Hinton
  • COURSERA: Neural Networks for Machine Learning, 2012. 16
  • 2012
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Deep Boltzmann Machines

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…