ArSyD learns image representations where each generative factor is a separate hypervector, enabling property editing by vector exchange and dimension-agnostic disentanglement evaluation.
Representation learning: A review and new perspectives.IEEE Transactions on Pattern Analysis and Machine Intelligence , 35(8):1798–1828, 2013
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Symbolic Disentangled Representations for Images
ArSyD learns image representations where each generative factor is a separate hypervector, enabling property editing by vector exchange and dimension-agnostic disentanglement evaluation.