mlsanityData to 14 Oct 2026

Generative Dataset Distillation using Min-Max Diffusion Model

arXiv 2503.18626 ↗First posted 24 Mar 2025cs.CVcited by 0

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

In this paper, we address the problem of generative dataset distillation that utilizes generative models to synthesize images. The generator may produce any number of images under a preserved evaluation time. In this work, we leverage the popular diffusion model as the generator to compute a surrogate dataset, boosted by a min-max loss to control the dataset's diversity and representativeness during training. However, the diffusion model is time-consuming when generating images, as it requires an iterative generation process. We observe a critical trade-off between the number of image samples and the image quality controlled by the diffusion steps and propose Diffusion Step Reduction to achieve optimal performance. This paper details our comprehensive method and its performance. Our model achieved 2nd place in the generative track of hrefhttps://www.dd-challenge.com/#/The First Dataset Distillation Challenge of ECCV2024, demonstrating its superior performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 19 of its 26 references that are in the map. First posted on arXiv 24 Mar 2025.

Builds on

19 of 26 references.

Closest ancestors · 7

Same direction, newest first

  1. 2022Scalable Diffusion Models with Transformers19 Dec
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  3. 2021Variational Diffusion Models1 Jul
  4. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  5. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  7. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 12

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  5. 2022Generative Adversarial Networkscited by 5,627
  6. 2017Generative Adversarial Networks: An Overviewcited by 590
  7. 2018Dataset Distillationcited by 230
  8. 2022Dataset Condensation via Efficient Synthetic-Data Parameterizationcited by 188
  9. 2023DREAM: Efficient Dataset Distillation by Representative Matchingcited by 94
  10. 2023Efficient Dataset Distillation via Minimax Diffusioncited by 83
  11. 2022DC-BENCH: Dataset Condensation Benchmarkcited by 67
  12. 2020How many images do I need? Understanding how sample size per class affects deep learning model performance metrics for balanced designs in autonomous wildlife monitoringcited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Generative Dataset Distillation Based on Diffusion Model
  2. 2024Data-Efficient Generation for Dataset Distillation
  3. 2025Diversity-Driven Generative Dataset Distillation Based on Diffusion Model with Self-Adaptive Memory
  4. 2025A Survey on Pre-Trained Diffusion Model Distillations
  5. 2024Towards Consistent and Efficient Dataset Distillation via Diffusion-Driven Selection
  6. 2024Simple and Fast Distillation of Diffusion Models
  7. 2025Taming Diffusion for Dataset Distillation with High Representativeness
  8. 2024Unlocking Dataset Distillation with Diffusion Models