Data Warmup accelerates diffusion training on ImageNet by scheduling images from low to high complexity via a foreground-based metric and temperature-controlled sampler, improving FID and IS scores faster than uniform sampling.
Pho- torealistic text-to-image diffusion models with deep language understanding.Advances in neural information processing systems, 35:36479–36494
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Data Warmup: Complexity-Aware Curricula for Efficient Diffusion Training
Data Warmup accelerates diffusion training on ImageNet by scheduling images from low to high complexity via a foreground-based metric and temperature-controlled sampler, improving FID and IS scores faster than uniform sampling.