mlsanityData to 14 Oct 2026

Efficient Denoising using Score Embedding in Score-based Diffusion Models

arXiv 2404.06661 ↗First posted 10 Apr 2024cs.CVcited by 1

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

It is well known that training a denoising score-based diffusion models requires tens of thousands of epochs and a substantial number of image data to train the model. In this paper, we propose to increase the efficiency in training score-based diffusion models. Our method allows us to decrease the number of epochs needed to train the diffusion model. We accomplish this by solving the log-density Fokker-Planck (FP) Equation numerically to compute the score textitbefore training. The pre-computed score is embedded into the image to encourage faster training under slice Wasserstein distance. Consequently, it also allows us to decrease the number of images we need to train the neural network to learn an accurate score. We demonstrate through our numerical experiments the improved performance of our proposed method compared to standard score-based diffusion models. Our proposed method achieves a similar quality to the standard method meaningfully faster.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 12 of its 18 references that are in the map. First posted on arXiv 10 Apr 2024.

Builds on

12 of 18 references.

Closest ancestors · 6

Same direction, newest first

  1. 2022FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck Equation9 Oct
  2. 2022Soft Diffusion: Score Matching for General Corruptions12 Sep
  3. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  5. 2020Denoising Diffusion Implicit Models6 Oct
  6. 2020Improved Techniques for Training Score-Based Generative Models16 Jun

Other references · 6

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  5. 2020Efficient Learning of Generative Models via Finite-Difference Score Matchingcited by 49
  6. 2023Efficient Pricing and Hedging of High Dimensional American Options Using Recurrent Networkscited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Efficient Score Pre-computation for Diffusion Models via Cross-Matrix Krylov Projectioncited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Score Augmentation for Diffusion Models
  2. 2021Maximum Likelihood Training of Score-Based Diffusion Models
  3. 2024Analyzing Neural Network-Based Generative Diffusion Models through Convex Optimization
  4. 2021Score-based diffusion models for accelerated MRI
  5. 2025Denoising Score Distillation: From Noisy Diffusion Pretraining to One-Step High-Quality Generation
  6. 2023Deep Networks as Denoising Algorithms: Sample-Efficient Learning of Diffusion Models in High-Dimensional Graphical Models
  7. 2024Bring Metric Functions into Diffusion Models
  8. 2024Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models