Unpaired Image-to-Image Translation with Domain Supervision

11 Feb 2019Jianxin Lin • Sen Liu • Yingce Xia • Shuxin Zhao • Tao Qin • Zhibo Chen

Image-to-image translation has been widely investigated in recent years. Existing approaches are elaborately designed in an unsupervised manner and little attention has been paid to domain information beneath unpaired data. Instead of representing domain characteristics with different generators in CycleGAN\cite{zhu2017unpaired} or multiple domain codes in StarGAN~\cite{choi2017stargan}, we pre-train a classification network to classify the domain of an image.

Full paper

Evaluation


No evaluation results yet. Help compare this paper to other papers by submitting the tasks and evaluation metrics from the paper.