Flow Factorized Representation Learning-Supplementary Material-Y ue Song 1,2, Andy Keller 2, Nicu Sebe 1, and Max Welling 2

Here we omit the computation of HJ PDEs for concisity. The model is trained for 90, 000 iterations. The model is also trained for 90, 000 iterations. For the disentanglement methods, we largely enrich the original MNIST dataset by adding the transformed images of the whole sequence. The generalization ability ( i.e., validation accuracy) can be thus regarded as a reasonable surrogate for the disentanglement ability.