Guiding a pretrained diffusion model toward per-class K-means centroids during sampling improves distilled dataset accuracy on ImageNet subsets by up to 4.4% while avoiding diffusion fine-tuning.
Due to its granularity of features, we trained DiT XL/2 on the ImageWoof dataset with just the simple loss mentioned in Eq
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MGD$^3$: Mode-Guided Dataset Distillation using Diffusion Models
Guiding a pretrained diffusion model toward per-class K-means centroids during sampling improves distilled dataset accuracy on ImageNet subsets by up to 4.4% while avoiding diffusion fine-tuning.