Improved Boundary Equilibrium Generative Adversarial Networks

Yanchun Li

doi:10.1109/ACCESS.2018.2804278

Improved Boundary Equilibrium Generative Adversarial Networks

2018-01-01

34

OA

AI

DOI：10.1109/ACCESS.2018.2804278

原文链接

查看原文

摘要

En 中文

Boundary equilibrium generative adversarial networks (BEGANs) can generate impressively realistic face images, but there is a trade-off between the quality and the diversity of generated images. Based on BEGANs, we propose an effective approach to generate images with higher quality and better diversity. By adding a second loss function (a denoising loss) to the discriminator, the discriminator can learn more useful information about the distribution of real images. Naturally, the ability of discriminator in distinguishing between real and generated images is improved, which further guides the generator to produce more realistic images to confuse the discriminator. We also find that using technique of batch normalization in BEGANs architecture can improve the diversity of generated images. By using batch normalization and adding a denoising loss to the objective of discriminator, we achieve comparative generations on CIFAR-10 and CelebA data sets. In addition, we evaluate the effect of several techniques on BEGANs framework through Inception-Score, a measure which has been found to correlate well with human assessment of generated samples.

Keyword:

Generative adversarial networks (GANs)

boundary equilibrium generative adversarial networks (BEGANs)

deep generative model

image generation

Improved Boundary Equilibrium Generative Adversarial Networks

摘要

AI总结

期刊

机构

引用论文