Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
Amjad Almahairi, Sai Rajeswar, Alessandro Sordoni, Philip Bachman, Aaron C. Courville · arXiv (Cornell University) · 2018
Learning inter-domain mappings from unpaired data can improve performance in structured prediction tasks, such as image segmentation, by reducing the need for paired data. CycleGAN was recently proposed for this problem, but critically assumes the underlying inter-domain mapping is approximately deterministic and one-to-one. This assumption renders the model ineffective for tasks requiring flexible, many-to-many mappings. We propose a new model, called Augmented CycleGAN, which learns many-to-many mappings between domains. We examine Augmented CycleGAN qualitatively and quantitatively on several image datasets.