2018 CGANswithProjectionDiscriminato

• (Miyato & Koyama, 2018) ⇒ Takeru Miyato, and Masanori Koyama. (2018). “cGANs with Projection Discriminator.” In: Proceedings of the 6th International Conference on Learning Representations (ICLR 2018), Conference Track Proceedings.

Subject Headings: Imagenet GAN Model; Generative Adversarial Network (GAN) Model.

Cited By

• Google Scholar: ~ 194 Citations Retrieved:2020-11-29.

Quotes

Author Keywords

• Generative Adversarial Networks; GANs; conditional GANs; Generative models; Projection

Abstract

We propose a novel, projection based way to incorporate the conditional information into the discriminator of GANs that respects the role of the conditional information in the underlining probabilistic model. This approach is in contrast with most frameworks of conditional GANs used in application today, which use the conditional information by concatenating the (embedded) conditional vector to the feature vectors. With this modification, we were able to significantly improve the quality of the class conditional image generation on ILSVRC2012 (ImageNet) 1000-class image dataset from the current state-of-the-art result, and we achieved this with a single pair of a discriminator and a generator. We were also able to extend the application to super-resolution and succeeded in producing highly discriminative super-resolution images. This new structure also enabled high quality category transformation based on parametric functional transformation of conditional batch normalization layers in the generator. The code with Chainer (Tokui et al., 2015), generated images and pretrained models are available https://github.com/pfnet-research/sngan_projection.

BibTeX

@inproceedings{2018_CGANswithProjectionDiscriminato,
  author    = {Takeru Miyato and
               Masanori Koyama},
  title     = {{GANs with Projection Discriminator},
  booktitle = {Proceedings of the 6th International Conference on Learning Representations (ICLR 2018),
               Conference Track Proceedings},
  publisher = {OpenReview.net},
  year      = {2018},
  url       = {https://openreview.net/forum?id=ByS1VpgRZ},
}

---

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2018 CGANswithProjectionDiscriminato	Takeru Miyato Masanori Koyama			cGANs with Projection Discriminator						2018