Non-Parametric Priors For Generative Adversarial Networks

@inproceedings{Singh2019NonParametricPF,
  title={Non-Parametric Priors For Generative Adversarial Networks},
  author={Rajhans Singh and Pavan K. Turaga and Suren Jayasuriya and Ravi Garg and Martin W. Braun},
  booktitle={ICML},
  year={2019}
}
The advent of generative adversarial networks (GAN) has enabled new capabilities in synthesis, interpolation, and data augmentation heretofore considered very challenging. However, one of the common assumptions in most GAN architectures is the assumption of simple parametric latent-space distributions. While easy to implement, a simple latent-space distribution can be problematic for uses such as interpolation. This is due to distributional mismatches when samples are interpolated in the latent… CONTINUE READING

Similar Papers

References

Publications referenced by this paper.
SHOWING 1-10 OF 33 REFERENCES

Distributioninterpolation trade off in generative models

D. Leśniak, I. Sieradzki, I. Podolak
  • In International Conference on Learning Representations (ICLR),
  • 2019
VIEW 25 EXCERPTS
HIGHLY INFLUENTIAL

Sampling Generative Networks

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Generative Adversarial Nets

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Deep Learning Face Attributes in the Wild

  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • 2014
VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL

Disentangling 3D Pose in a Dendritic CNN for Unconstrained 2D Face Alignment

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
VIEW 1 EXCERPT