Guiding the One-to-One Mapping in CycleGAN via Optimal Transport


  • Guansong Lu Shanghai Jiao Tong University
  • Zhiming Zhou Shanghai Jiao Tong University
  • Yuxuan Song Shanghai Jiao Tong University
  • Kan Ren Shanghai Jiao Tong University
  • Yong Yu Shanghai Jiao Tong University



CycleGAN is capable of learning a one-to-one mapping between two data distributions without paired examples, achieving the task of unsupervised data translation. However, there is no theoretical guarantee on the property of the learned one-to-one mapping in CycleGAN. In this paper, we experimentally find that, under some circumstances, the one-to-one mapping learned by CycleGAN is just a random one within the large feasible solution space. Based on this observation, we explore to add extra constraints such that the one-to-one mapping is controllable and satisfies more properties related to specific tasks. We propose to solve an optimal transport mapping restrained by a task-specific cost function that reflects the desired properties, and use the barycenters of optimal transport mapping to serve as references for CycleGAN. Our experiments indicate that the proposed algorithm is capable of learning a one-to-one mapping with the desired properties.




How to Cite

Lu, G., Zhou, Z., Song, Y., Ren, K., & Yu, Y. (2019). Guiding the One-to-One Mapping in CycleGAN via Optimal Transport. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 4432-4439.



AAAI Technical Track: Machine Learning