Spectrally Normalised GAN

Introduced by Miyato et al. in Spectral Normalization for Generative Adversarial Networks

SNGAN, or Spectrally Normalised GAN, is a type of generative adversarial network that uses spectral normalization, a type of weight normalization, to stabilise the training of the discriminator.

Source: Spectral Normalization for Generative Adversarial Networks

Latest Papers

PAPER DATE
Improving the Speed and Quality of GAN by Adversarial Training
Jiachen ZhongXuanqing LiuCho-Jui Hsieh
2020-08-07
PriorGAN: Real Data Prior for Generative Adversarial Nets
Shuyang GuJianmin BaoDong ChenFang Wen
2020-06-30
Synthesizing Unrestricted False Positive Adversarial Objects Using Generative Models
Martin KotuliakSandro E. SchoenbornAndrei Dan
2020-05-19
Mimicry: Towards the Reproducibility of GAN Research
| Kwot Sin LeeChristopher Town
2020-05-05
LOGAN: Latent Optimisation for Generative Adversarial Networks
| Yan WuJeff DonahueDavid BalduzziKaren SimonyanTimothy Lillicrap
2019-12-02
Deep Compressed Sensing
| Yan WuMihaela RoscaTimothy Lillicrap
2019-05-16
Spectral Normalization for Generative Adversarial Networks
| Takeru MiyatoToshiki KataokaMasanori KoyamaYuichi Yoshida
2018-02-16

Tasks

TASK PAPERS SHARE
Image Generation 3 42.86%
Object Detection 1 14.29%
Conditional Image Generation 1 14.29%
Meta-Learning 1 14.29%
adversarial training 1 14.29%

Categories