AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

DMGD: Train-Free Dataset Distillation with Semantic-Distribution Matching in Diffusion Models

Qichao Wang, Yunhong Lu, Hengyuan Cao, Junyi Zhang, Min Zhang

CVPR 2026 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add semantic matching (dynamic soft-label guidance) to DiT (ablation)DMGD · ImageNet-Woof IPC-50top-1 accuracy: 49.3 -> 59.3Improved
add semantic matching to DiT (ablation)DMGD · ImageNet-Woof IPC-10top-1 accuracy: 34.7 -> 38.9Improved
add distribution matching (OT guidance) to DiT (ablation)DMGD · ImageNet-Woof IPC-10top-1 accuracy: 34.7 -> 41.6Improved
add distribution matching to DiT (ablation)DMGD · ImageNet-Woof IPC-50top-1 accuracy: 49.3 -> 56.8Improved
add distribution matching to semantic matching (ablation)DMGD · ImageNet-Woof IPC-50top-1 accuracy: 59.3 -> 60.1Improved
add semantic matching to distribution matching (ablation)DMGD · ImageNet-Woof IPC-50top-1 accuracy: 56.8 -> 60.1Improved
add semantic matching to distribution matching (ablation)DMGD · ImageNet-Woof IPC-10top-1 accuracy: 41.6 -> 40.8Hurt
add distribution matching to semantic matching (ablation)DMGD · ImageNet-Nette IPC-10top-1 accuracy: 67.1 -> 68.4Improved
add distribution matching to semantic matching (ablation)DMGD · ImageNet-Nette IPC-50top-1 accuracy: 79.7 -> 80.6Improved
plug DMGD into MiniMaxMiniMax · ImageNet-Nette IPC-10top-1 accuracy: 62.0 -> 68.7Improved
plug DMGD into DiTDiT · ImageNet-Woof IPC-50top-1 accuracy: 49.3 -> 60.1Improved
use DMGD instead of MGD3 on Woof IPC-50DiT + DMGD · ImageNet-Woof IPC-50top-1 accuracy: 56.5 -> 60.1Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy