• Mathematics, Computer Science
  • Published in ArXiv 2020

Improved Consistency Regularization for GANs

@article{Zhao2020ImprovedCR,
  title={Improved Consistency Regularization for GANs},
  author={Zhengli Zhao and Sameer Singh and Honglak Lee and Zizhao Zhang and Augustus Odena and Han Zhang},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.04724}
}
Recent work (Zhang et al., 2020) has increased the performance of Generative Adversarial Networks (GANs) by enforcing a consistency cost on the discriminator. We improve on this technique in several ways. We first show that consistency regularization can introduce artifacts into the GAN samples and explain how to fix this issue. We then propose several modifications to the consistency regularization procedure designed to improve its performance. We carry out extensive experiments quantifying… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 40 REFERENCES

Large Scale GAN Training for High Fidelity Natural Image Synthesis

VIEW 13 EXCERPTS
HIGHLY INFLUENTIAL

Improved Training of Wasserstein GANs

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Improved Techniques for Training GANs

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Deep Residual Learning for Image Recognition

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Generative Adversarial Nets

VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL