mlsanityData to 14 Oct 2026

Diffusion-GAN: Training GANs with Diffusion

arXiv 2206.02262 ↗First posted 5 Jun 2022cs.LG stat.MLcited by 205

Not on the map. Why?

Cited by 131 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Generative adversarial networks (GANs) are challenging to train stably, and a promising remedy of injecting instance noise into the discriminator input has not been very effective in practice. In this paper, we propose Diffusion-GAN, a novel GAN framework that leverages a forward diffusion chain to generate Gaussian-mixture distributed instance noise. Diffusion-GAN consists of three components, including an adaptive diffusion process, a diffusion timestep-dependent discriminator, and a generator. Both the observed and generated data are diffused by the same adaptive diffusion process. At each diffusion timestep, there is a different noise-to-data ratio and the timestep-dependent discriminator learns to distinguish the diffused real data from the diffused generated data. The generator learns from the discriminator's feedback by backpropagating through the forward diffusion chain, whose length is adaptively adjusted to balance the noise and data levels. We theoretically show that the discriminator's timestep-dependent strategy gives consistent and helpful guidance to the generator, enabling it to match the true data distribution. We demonstrate the advantages of Diffusion-GAN over strong GAN baselines on various datasets, showing that it can produce more realistic images with higher stability and data efficiency than state-of-the-art GANs.

Key facts. Cited by 205 papers in the map (data through 14 Oct 2026). Builds on 54 of its 76 references that are in the map. First posted on arXiv 5 Jun 2022.

Builds on

54 of 76 references.

References · 54

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  8. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  9. 2013Auto-Encoding Variational Bayescited by 4,053
  10. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  11. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  12. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
38 more
  1. 2016Improved Techniques for Training GANscited by 2,970
  2. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  3. 2017Improved Training of Wasserstein GANscited by 2,235
  4. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  5. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  6. 2016Variational Inference: A Review for Statisticianscited by 1,472
  7. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  8. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  9. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,179
  10. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
  11. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  12. 2018Self-Attention Generative Adversarial Networkscited by 809
  13. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 700
  14. 2018Which Training Methods for GANs do actually Converge?cited by 679
  15. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 577
  16. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 516
  17. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 506
  18. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 464
  19. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 363
  20. 2016Adversarial Feature Learningcited by 350
  21. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speedcited by 348
  22. 2017MMD GAN: Towards Deeper Understanding of Moment Matching Networkcited by 254
  23. 2016Adversarially Learned Inferencecited by 216
  24. 2021Projected GANs Converge Fastercited by 208
  25. 2021On Fast Sampling of Diffusion Probabilistic Modelscited by 170
  26. 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
  27. 2019Consistency Regularization for Generative Adversarial Networkscited by 136
  28. 2017The Cramer Distance as a Solution to Biased Wasserstein Gradientscited by 119
  29. 2017Stabilizing Training of Generative Adversarial Networks through Regularizationcited by 118
  30. 2018Generative Modeling using the Sliced Wasserstein Distancecited by 108
  31. 2020Image Generators with Conditionally-Independent Pixel Synthesiscited by 106
  32. 2017The Numerics of GANscited by 105
  33. 2022DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latentscited by 104
  34. 2021Noise Estimation for Generative Diffusion Modelscited by 94
  35. 2016Amortised MAP Inference for Image Super-resolutioncited by 68
  36. 2021Data-Efficient Instance Generation from Instance Discriminationcited by 58
  37. 2017Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Stepcited by 45
  38. 2022Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoderscited by 42

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 13; 2023: 48; 2024: 70; 2025: 56; 2026: 18.

205 papers.

Sort:

By area:

  1. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  2. 2023One-step Diffusion with Distribution Matching Distillationcited by 1,019
  3. 2022Diffusion Models in Vision: A Surveycited by 1,015
  4. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 938
  5. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 684
  6. 2022Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learningcited by 562
  7. 2023UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Modelscited by 450
  8. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 395
  9. 2024Simplifying, Stabilizing and Scaling Continuous-Time Consistency Modelscited by 283
  10. 2024Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generationcited by 214
  11. 2023Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion modelscited by 205
  12. 2023UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANscited by 166
38 more
  1. 2023Raising the Bar of AI-generated Image Detection with CLIPcited by 164
  2. 2023Flow Matching in Latent Spacecited by 160
  3. 2025Diffusion Adversarial Post-Training for One-Step Video Generationcited by 151
  4. 2023Hierarchical Fine-Grained Image Forgery Detection and Localizationcited by 134
  5. 2023Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Modelscited by 133
  6. 2022Towards the Detection of Diffusion Model Deepfakescited by 111
  7. 2023In-Context Learning Unlocked for Diffusion Modelscited by 104
  8. 2022Refining Generative Process with Discriminator Guidance in Score-based Diffusion Modelscited by 100
  9. 2024PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Acceleratorcited by 97
  10. 2024One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillationcited by 89
  11. 2025SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillationcited by 87
  12. 2023Optimizing DDPM Sampling with Shortcut Fine-Tuningcited by 81
  13. 2023HumanMAC: Masked Motion Completion for Human Motion Predictioncited by 81
  14. 2024Distilling Diffusion Models into Conditional GANscited by 78
  15. 2024Accelerating Convergence of Score-Based Diffusion Models, Provablycited by 76
  16. 2023SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Modelscited by 72
  17. 2024One-Step Diffusion Distillation through Score Implicit Matchingcited by 71
  18. 2022Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidancecited by 67
  19. 2024Accelerating Diffusion Sampling with Optimized Time Stepscited by 67
  20. 2023AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectorscited by 64
  21. 2024Adversarial Diffusion Compression for Real-World Image Super-Resolutioncited by 52
  22. 2022Efficient Diffusion Models for Vision: A Surveycited by 51
  23. 2024AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policiescited by 50
  24. 2024Zero-Shot Detection of AI-Generated Imagescited by 50
  25. 2024Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Stepcited by 47
  26. 2024Light and Optimal Schr"odinger Bridge Matchingcited by 45
  27. 2024Diffusion Policies creating a Trust Region for Offline Reinforcement Learningcited by 43
  28. 2024RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detectioncited by 36
  29. 2025Continuously Augmented Discrete Diffusion model for Categorical Generative Modelingcited by 34
  30. 2024Diffusion-RPO: Aligning Diffusion Models through Relative Preference Optimizationcited by 32
  31. 2025SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillationcited by 32
  32. 2024SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Trainingcited by 27
  33. 2023DS-Fusion: Artistic Typography via Discriminated and Stylized Diffusioncited by 26
  34. 2024You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANscited by 26
  35. 2025Unleashing Vecset Diffusion Model for Fast Shape Generationcited by 26
  36. 2024Training Unbiased Diffusion Models From Biased Datasetcited by 25
  37. 2023Cousins Of The Vendi Score: A Family Of Similarity-Based Diversity Metrics For Science And Machine Learningcited by 24
  38. 2024CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Modelscited by 24

50 most cited of 205 All 205 (JSON)