- Casey Chu
- Andrey Zhmoginov
- Mark Sandler
NIPS 2017 Workshop “Machine Deception” (2017)
CycleGAN is one of the latest successful approaches to learning a correspondence between two distinct probability distributions. However, it may not always be possible or easy to find a natural one-to-one mapping between two domains. We demonstrate that in such cases CycleGAN model tends to "hide" at least some information about the input sample in the indistinguishable noise added to the output. This makes the network output look "realistic", while also allowing the complementary transformation to recover the original sample and thus satisfy cycle consistency requirement.
We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work