Classifier-free guidance trades off sample quality and diversity in conditional diffusion models by combining scores from jointly trained conditional and unconditional models.
A connection between score matching and denoising autoencoders
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Metropolis-adjusted Langevin correctors using score-based acceptance probabilities, including an exact Bernoulli factory method and a Simpson's rule approximation, reduce sampling bias in diffusion models and improve FID scores.
citing papers explorer
-
Classifier-Free Diffusion Guidance
Classifier-free guidance trades off sample quality and diversity in conditional diffusion models by combining scores from jointly trained conditional and unconditional models.
-
Metropolis-Adjusted Diffusion Models
Metropolis-adjusted Langevin correctors using score-based acceptance probabilities, including an exact Bernoulli factory method and a Simpson's rule approximation, reduce sampling bias in diffusion models and improve FID scores.