Unsupervised doman translation using normalizing flows

I introduce a probabilistic framework to learn a bijective mapping between two domains using only unpaired data. The framework uses invertible layers with tractable determinant-jacobians to find the mapping using exact likelihood training. You can find some preliminary code at this Github repo. If you’ve got a nifty application that stands to benifit from this invertible framework, get in touch.

The talk was part of the PechaKucha series conducted by Girton, MCR. Finally, some pictures from the talk, aplogies for the poor quality. In the future, perhaps I will find some time to apply unpaired domain translation to brighten and sharpen images!