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.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2019 2verdicts
UNVERDICTED 2representative citing papers
Presents HABP to emphasize hard samples during training and Deact to generate stable synthetic samples for rare attributes, outperforming prior methods on large-scale fashion datasets without extra supervision.
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.
-
Hard-Aware Fashion Attribute Classification
Presents HABP to emphasize hard samples during training and Deact to generate stable synthetic samples for rare attributes, outperforming prior methods on large-scale fashion datasets without extra supervision.