Proposes PrOSe parameterization of latent space as product of orthogonal spheres to improve disentangled representation learning, with closed-form ortho-normality loss under equal block size assumption.
Why deep learning works: A manifold disentanglement perspective
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Product of Orthogonal Spheres Parameterization for Disentangled Representation Learning
Proposes PrOSe parameterization of latent space as product of orthogonal spheres to improve disentangled representation learning, with closed-form ortho-normality loss under equal block size assumption.