We take the novel perspective to view data not merely as a probability distribution but as a current. Primarily studied in the field of geometric measure theory, k-currents are continuous linear functionals acting on compactly supported smooth differential forms and can be understood as a generalized notion of oriented k-dimensional manifold. By moving from distributions (which are 0-currents) to k-currents, we can explicitly orient the data by attaching a k-dimensional tangent plane to each sample point. Based on the flat metric which is a fundamental distance between currents, we derive FlatGAN, a formulation in the spirit of generative adversarial networks but generalized to k-currents. In our theoretical contribution we prove that the flat metric between a parametrized current and a reference current is continuous in the parameters. In experiments, we show that the proposed shift to k>0 leads to interpretable and disentangled latent representations which behave equivariantly to the specified oriented tangent planes.
Thomas Möllenhoff (TU Munich)
Daniel Cremers (TU Munich)
Related Events (a corresponding poster, oral, or spotlight)
2019 Poster: Flat Metric Minimization with Applications in Generative Modeling »
Tue Jun 11th 06:30 -- 09:00 PM Room Pacific Ballroom