23 Downloads (Pure)

Samenvatting

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.
Originele taal-2Engels
StatusGepubliceerd - 26 nov 2020
EvenementNeurIPS 2020 workshop on Differential Geometry meets Deep Learning - Online
Duur: 11 dec 202011 dec 2020
https://sites.google.com/view/diffgeo4dl/call-for-papers?authuser=0

Workshop

WorkshopNeurIPS 2020 workshop on Differential Geometry meets Deep Learning
Verkorte titelDiffGeo4DL
Periode11/12/2011/12/20
Internet adres

Citeer dit