南京理工大学学报（自然科学版）2019，Vol.43Issue(1)：35-40,6.DOI:10.14177/j.cnki.32-1397n.2019.43.01.005
迭代化代价函数及超参数可变的生成对抗网络
Iterative cost function and variable parameter generative adversarial networks
摘要
Abstract
In order to solve the difficult training problem of generative adversarial networks, this paper proposes an iterative cost function and variable parameter generative adversarial networks based on the Wasserstein GAN ( WGAN ) method. For the improvement of penalty items in the original WGAN, iterative methods are used to increase penalty instead of the original randomly selected method. Aiming at the hyper-parameter of penalty item of fixed cost function in WGAN,the strategy of changing hyper-parameter is put forward. The change is based on the distance between imitation distribution and real distribution. Experiments conducted on MNIST handwritten font datasets and CELEBA face datasets show the effectiveness of the proposed method as compared with the traditional WGAN,significantly improving the convergence speed of the generator.关键词
生成对抗网络/迭代化代价函数/超参数可变/分布距离Key words
generative adversarial networks/ iterative cost function method/ variable parameter/distribution distance分类
信息技术与安全科学引用本文复制引用
陈耀,宋晓宁,於东军..迭代化代价函数及超参数可变的生成对抗网络[J].南京理工大学学报（自然科学版）,2019,43(1):35-40,6.基金项目
国家自然科学基金(61876072) （61876072）
国家重点研发计划子课题(2017YFC1601800) （2017YFC1601800）
中国博士后科学基金特助(2018T110441) （2018T110441）
江苏省自然科学基金(BK20161135) （BK20161135）
江苏省"六大人才高峰"资助(XYDXX-012) （XYDXX-012）
