Entropy-driven Sampling and Training Scheme for Conditional Diffusion Generation. (arXiv:2206.11474v1 [cs.CV])

Denoising Diffusion Probabilistic Model (DDPM) is able to make flexible
conditional image generation from prior noise to real data, by introducing an
independent noise-aware classifier to provide conditional gradient guidance at
each time step of denoising process. However, due to the ability of classifier
to easily discriminate an incompletely generated image only with high-level
structure, the gradient, which is a kind of class information guidance, tends
to vanish early, leading to the collapse from conditional generation process
into the unconditional …

arxiv cv diffusion entropy generation sampling training