Targeted tweaks to DDPMs produce competitive likelihoods and high-quality samples, with learned reverse variances enabling 10x faster sampling and predictable scaling with compute.
This is similar to VQ-V AE-2 (Razavi et al., 2019), which uses two stages of priors at different latent resolutions to more efficiently learn global and local features
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2021 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Improved Denoising Diffusion Probabilistic Models
Targeted tweaks to DDPMs produce competitive likelihoods and high-quality samples, with learned reverse variances enabling 10x faster sampling and predictable scaling with compute.