Tao Zhang1,2, Zhanjie Zhang1,2,*, Wenjing Jia3, Xiangjian He3, Jie Yang4
CMC-Computers, Materials & Continua, Vol.69, No.2, pp. 2733-2747, 2021, DOI:10.32604/cmc.2021.019305
Abstract The generative adversarial network (GAN) is first proposed in 2014, and this kind of network model is machine learning systems that can learn to measure a given distribution of data, one of the most important applications is style transfer. Style transfer is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image. CYCLE-GAN is a classic GAN model, which has a wide range of scenarios in style transfer. Considering its unsupervised learning characteristics, the mapping is easy to be learned between an input image and an output… More >
Login
Register
