A VAE trained with a hand-built hyperspherical-coordinate regularizer compresses latent codes into a small region of the sphere and appears to improve decoded sample quality, though the reported generation protocol uses a distribution fitted to test latents.
Concentration of measure,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Improving the Generation of VAEs with High Dimensional Latent Spaces by the use of Hyperspherical Coordinates
A VAE trained with a hand-built hyperspherical-coordinate regularizer compresses latent codes into a small region of the sphere and appears to improve decoded sample quality, though the reported generation protocol uses a distribution fitted to test latents.