ARTFEED — Contemporary Art Intelligence

DMGD: Training-Free Dataset Distillation via Diffusion Models

other · 2026-05-07

A new framework called Dual Matching Guided Diffusion (DMGD) proposes training-free dataset distillation using semantic and distribution matching. It eliminates the need for fine-tuning by optimizing conditional likelihood for semantic alignment and employs optimal transport for distribution matching. The method enhances synthetic data diversity while maintaining alignment with original datasets.

Key facts

  • DMGD stands for Dual Matching Guided Diffusion.
  • The framework is training-free, requiring no fine-tuning.
  • Semantic Matching uses conditional likelihood optimization.
  • A dynamic guidance mechanism improves synthetic data diversity.
  • Optimal transport (OT) based Distribution Matching aligns distributions.
  • The approach addresses limitations of diffusion-based dataset distillation.
  • The paper is available on arXiv with ID 2605.03877v1.
  • The method eliminates the need for auxiliary classifiers.

Entities

Institutions

  • arXiv

Sources