mlsanityData to 14 Oct 2026

Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models

arXiv 2211.17091 ↗First posted 28 Nov 2022cs.CV cs.AI cs.LGcited by 100

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

The proposed method, Discriminator Guidance, aims to improve sample generation of pre-trained diffusion models. The approach introduces a discriminator that gives explicit supervision to a denoising sample path whether it is realistic or not. Unlike GANs, our approach does not require joint training of score and discriminator networks. Instead, we train the discriminator after score training, making discriminator training stable and fast to converge. In sample generation, we add an auxiliary term to the pre-trained score to deceive the discriminator. This term corrects the model score to the data score at the optimal discriminator, which implies that the discriminator helps better score estimation in a complementary way. Using our algorithm, we achive state-of-the-art results on ImageNet 256x256 with FID 1.83 and recall 0.64, similar to the validation data's FID (1.68) and recall (0.66). We release the code at https://github.com/alsdudrla10/DG.

Key facts. Cited by 100 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 47 of its 78 references that are in the map. First posted on arXiv 28 Nov 2022.

Builds on

47 of 78 references.

Closest ancestors · 19

Same direction, newest first

  1. 2022Soft Diffusion: Score Matching for General Corruptions12 Sep
  2. 2022Convergence of denoising diffusion models under the manifold hypothesis10 Aug
  3. 2022Entropy-driven Sampling and Training Scheme for Conditional Diffusion Generation23 Jun
  4. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  5. 2022Maximum Likelihood Training of Implicit Nonlinear Diffusion Models27 May
  6. 2022Accelerating Diffusion Models via Early Stop of the Diffusion Process25 May
  7. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  8. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANs15 Dec
  9. 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusion14 Dec
  10. 2021Variational Diffusion Models1 Jul
  11. 2021Score-based Generative Modeling in Latent Space10 Jun
  12. 2021Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation10 Jun
7 more
  1. 2021Cascaded Diffusion Models for High Fidelity Image Generation30 May
  2. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  3. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  4. 2021Maximum Likelihood Training of Score-Based Diffusion Models22 Jan
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  6. 2020Denoising Diffusion Implicit Models6 Oct
  7. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 28

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  3. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  5. 2022Generative Adversarial Networkscited by 5,627
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  8. 2013Auto-Encoding Variational Bayescited by 4,053
  9. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  10. 2022Video Diffusion Modelscited by 2,305
  11. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  12. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
16 more
  1. 2022Denoising Diffusion Restoration Modelscited by 963
  2. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 506
  3. 2022MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolationcited by 309
  4. 2021Generating Images with Sparse Representationscited by 266
  5. 2022Dual Diffusion Implicit Bridges for Image-to-Image Translationcited by 213
  6. 2022Diffusion-GAN: Training GANs with Diffusioncited by 205
  7. 2020Telescoping Density-Ratio Estimationcited by 108
  8. 2014On the relation between optimal transport and Schr"odinger bridges: A stochastic control viewpointcited by 99
  9. 2020Adversarial score matching and improved sampling for image generationcited by 96
  10. 2020Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Samplingcited by 71
  11. 2020A Contrastive Learning Approach for Training Variational Autoencoder Priorscited by 66
  12. 2018Resampled Priors for Variational Autoencoderscited by 57
  13. 2018Discriminator Rejection Samplingcited by 49
  14. 2022Denoising Likelihood Score Matching for Conditional Score-based Data Generationcited by 46
  15. 2020Non-Negative Bregman Divergence Minimization for Deep Direct Density Ratio Estimationcited by 45
  16. 2018Metropolis-Hastings Generative Adversarial Networkscited by 41

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 30; 2024: 28; 2025: 24; 2026: 18.

100 papers.

Sort:

By area:

  1. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusioncited by 459
  2. 2023Improved Techniques for Training Consistency Modelscited by 439
  3. 2024Guiding a Diffusion Model with a Bad Version of Itselfcited by 299
  4. 2023CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Samplingcited by 129
  5. 2023One-Step Diffusion Distillation via Deep Equilibrium Modelscited by 61
  6. 2023A Comprehensive Survey on Knowledge Distillation of Diffusion Modelscited by 45
  7. 2023Exact Diffusion Inversion via Bi-directional Integration Approximationcited by 44
  8. 2023GSURE-Based Diffusion Model Training with Corrupted Datacited by 40
  9. 2024Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studiescited by 38
  10. 2023Don't Play Favorites: Minority Guidance for Diffusion Modelscited by 37
  11. 2024Self-Improving Diffusion Models with Synthetic Datacited by 35
  12. 2023Blackout Diffusion: Generative Diffusion Models in Discrete-State Spacescited by 30
38 more
  1. 2023Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scalecited by 26
  2. 2024Training Unbiased Diffusion Models From Biased Datasetcited by 25
  3. 2024MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generationcited by 23
  4. 2025Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminatorcited by 23
  5. 2023Diffusion Model with Perceptual Losscited by 21
  6. 2025Training-Free Safe Denoisers for Safe Use of Diffusion Modelscited by 21
  7. 2023Spiking Denoising Diffusion Probabilistic Modelscited by 19
  8. 2023DiffEnc: Variational Diffusion with a Learned Encodercited by 17
  9. 2025Visual Generation Without Guidancecited by 17
  10. 2024Label-Noise Robust Diffusion Modelscited by 16
  11. 2024An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat Landscapecited by 16
  12. 2023Correcting Diffusion Generation through Resamplingcited by 15
  13. 2025MixerMDM: Learnable Composition of Human Motion Diffusion Modelscited by 13
  14. 2025Dynamic Classifier-Free Diffusion Guidance via Online Feedbackcited by 13
  15. 2023Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedbackcited by 12
  16. 2025Adversarial Flow Modelscited by 12
  17. 2024Structure-Guided Adversarial Training of Diffusion Modelscited by 11
  18. 2024Diffusion Rejection Samplingcited by 11
  19. 2023On the Equivalence of Consistency-Type Models: Consistency Models, Consistent Diffusion Models, and Fokker-Planck Regularizationcited by 10
  20. 2025Solving Linear-Gaussian Bayesian Inverse Problems with Decoupled Diffusion Sequential Monte Carlocited by 10
  21. 2023Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flowscited by 9
  22. 2024Stable Consistency Tuning: Understanding and Improving Consistency Modelscited by 9
  23. 2025Preference Optimization by Estimating the Ratio of the Data Distributioncited by 9
  24. 2023On Accelerating Diffusion-Based Sampling Process via Improved Integration Approximationcited by 8
  25. 2024Localize, Understand, Collaborate: Semantic-Aware Dragging via Intention Reasonercited by 8
  26. 2024DLCR: A Generative Data Expansion Framework via Diffusion for Clothes-Changing Person Re-IDcited by 8
  27. 2025Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Modelscited by 8
  28. 2023Revisiting the Evaluation of Image Synthesis with GANscited by 7
  29. 2023Raising the Bar for Certified Adversarial Robustness with Diffusion Modelscited by 7
  30. 2023Score Mismatching for Generative Modelingcited by 7
  31. 2024GeoGuide: Geometric guidance of diffusion modelscited by 7
  32. 2024AutoLoRA: AutoGuidance Meets Low-Rank Adaptation for Diffusion Modelscited by 7
  33. 2023Don't be so negative! Score-based Generative Modeling with Oracle-assisted Guidancecited by 6
  34. 2023Assessing Robustness via Score-Based Adversarial Image Generationcited by 6
  35. 2023Unsupervised Discovery of Interpretable Directions in h-space of Pre-trained Diffusion Modelscited by 6
  36. 2024Simple Drop-in LoRA Conditioning on Attention Layers Will Improve Your Diffusion Modelcited by 6
  37. 2024Diffusion Bridge AutoEncoders for Unsupervised Representation Learningcited by 6
  38. 2024GenFormer -- Generated Images are All You Need to Improve Robustness of Transformers on Small Datasetscited by 6

50 most cited of 100 All 100 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023DiffFlow: A Unified SDE Framework for Score-Based Diffusion Models and Generative Adversarial Networks
  2. 2024A Score-Based Density Formula, with Applications in Diffusion Generative Models
  3. 2025Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation
  4. 2026Where the Score Lives: A Wavelet View of Diffusion
  5. 2022Progressive Distillation for Fast Sampling of Diffusion Models
  6. 2023Diffusion Models Beat GANs on Image Classification
  7. 2026From Score Learning to Discretized Sampling: An End-to-End Generalization Analysis of Diffusion Models
  8. 2025ADT: Tuning Diffusion Models with Adversarial Supervision