An initial continuous autoencoder training phase prevents dimensional collapse in VQ-VAEs and yields lower reconstruction and perceptual losses.
A Proofs for Section 3 A.1 Dense RD-AE flow We derive (6)–(7) using the notation of Section 3.1
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Continuous First, Discrete Later: VQ-VAEs Without Dimensional Collapse
An initial continuous autoencoder training phase prevents dimensional collapse in VQ-VAEs and yields lower reconstruction and perceptual losses.