当前位置: X-MOL 学术Neural Netw. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Generative adversarial networks with mixture of t-distributions noise for diverse image generation.
Neural Networks ( IF 6.0 ) Pub Date : 2019-11-18 , DOI: 10.1016/j.neunet.2019.11.003
Jinxuan Sun 1 , Guoqiang Zhong 1 , Yang Chen 1 , Yongbin Liu 1 , Tao Li 1 , Kaizhu Huang 2
Affiliation  

Image generation is a long-standing problem in the machine learning and computer vision areas. In order to generate images with high diversity, we propose a novel model called generative adversarial networks with mixture of t-distributions noise (tGANs). In tGANs, the latent generative space is formulated using a mixture of t-distributions. Particularly, the parameters of the components in the mixture of t-distributions can be learned along with others in the model. To improve the diversity of the generated images in each class, each noise vector and a class codeword are concatenated as the input of the generator of tGANs. In addition, a classification loss is added to both the generator and the discriminator losses to strengthen their performances. We have conducted extensive experiments to compare tGANs with a state-of-the-art pixel by pixel image generation approach, pixelCNN, and related GAN-based models. The experimental results and statistical comparisons demonstrate that tGANs perform significantly better than pixleCNN and related GAN-based models for diverse image generation.

中文翻译:

具有t分布噪声混合的生成对抗网络,可用于生成多种图像。

在机器学习和计算机视觉领域,图像生成是一个长期存在的问题。为了生成具有高度多样性的图像,我们提出了一种新的模型,称为混合对抗网络,该网络具有t分布噪声(tGAN)的混合。在tGAN中,潜在的生成空间是使用t分布的混合物制定的。特别是,可以与模型中的其他分布一起了解t分布混合中各成分的参数。为了改善每个类别中所生成图像的多样性,将每个噪声矢量和一个类别码字串联起来,作为tGAN生成器的输入。另外,分类损失被添加到生成器损失和鉴别器损失两者上,以增强其性能。我们进行了广泛的实验,将tGAN与最新的逐像素图像生成方法,pixelCNN和相关的基于GAN的模型进行比较。实验结果和统计比较表明,对于多种图像生成,tGAN的性能明显优于pixleCNN和相关的基于GAN的模型。
更新日期:2019-11-18
down
wechat
bug