A Metric for Linear Symmetry-Based Disentanglement

11/26/2020
by   Luis A. Pérez Rey, et al.
0

The definition of Linear Symmetry-Based Disentanglement (LSBD) proposed by (Higgins et al., 2018) outlines the properties that should characterize a disentangled representation that captures the symmetries of data. However, it is not clear how to measure the degree to which a data representation fulfills these properties. We propose a metric for the evaluation of the level of LSBD that a data representation achieves. We provide a practical method to evaluate this metric and use it to evaluate the disentanglement of the data representations obtained for three datasets with underlying SO(2) symmetries.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset