Generative model with normalized pairwise distance constraint discovers output space topologies from sparse data and outperforms GANs and VAEs by avoiding mode collapse.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Neural Embedding for Physical Manipulations
Generative model with normalized pairwise distance constraint discovers output space topologies from sparse data and outperforms GANs and VAEs by avoiding mode collapse.