Learning disentangled representations via product manifold projection

Understand

We propose a novel approach to disentangle the generative factors of variation underlying a given set of observations.

• Our method builds upon the idea that the (unknown) low-dimensional manifold underlying the data space can be explicitly modeled as a product of submanifolds.
• This definition of disentanglement gives rise to a novel weakly-supervised algorithm for recovering the unknown explanatory factors behind the data.
• At training time, our algorithm only requires pairs of non i.i.d.