2018 SpectralNormalizationforGenerat

• (Miyato et al., 2018) ⇒ Takeru Miyato, Toshiki Kataoka, Masanori Koyama, and Yuichi Yoshida. (2018). “Spectral Normalization for Generative Adversarial Networks.” In: Proceedings of the Sixth International Conference on Learning Representations (ICLR-2018).

Subject Headings: GAN Algorithm.

Notes

• Slides at https://takerum.github.io/pdfs/sn_slides.pdf
• Code, generated images, and pretrained models are available at: https://github.com/pfnet-research/sngan_projection

Cited By

• http://scholar.google.com/scholar?q=%222018%22+Spectral+Normalization+for+Generative+Adversarial+Networks

2018

• Chainer-GAN-lib: https://github.com/pfnet-research/chainer-gan-lib
  • QUOTE: Consecutive category morphing movies:

   (5x5 panels 128px images) https://www.youtube.com/watch?v=q3yy5Fxs7Lc
   (10x10 panels 128px images) https://www.youtube.com/watch?v=83D_3WXpPjQ

Quotes

Abstract

One of the challenges in the study of generative adversarial networks is the instability of its training. In this paper, we propose a novel weight normalization technique called spectral normalization to stabilize the training of the discriminator. Our new normalization technique is computationally light and easy to incorporate into existing implementations. We tested the efficacy of spectral normalization on CIFAR10, STL-10, and ILSVRC2012 dataset, and we experimentally confirmed that spectrally normalized GANs (SN-GANs) is capable of generating images of better or equal quality relative to the previous training stabilization techniques.

References

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2018 SpectralNormalizationforGenerat	Yuichi Yoshida Takeru Miyato Toshiki Kataoka Masanori Koyama			Spectral Normalization for Generative Adversarial Networks