mlsanityData to 7 Oct 2026

Demystifying MMD GANs

arXiv 1801.01401 ↗First posted 4 Jan 2018stat.ML cs.LGcited by 1,268

Not on the map. Why?

Cited by 409 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We investigate the training and performance of generative adversarial networks using the Maximum Mean Discrepancy (MMD) as critic, termed MMD GANs. As our main theoretical contribution, we clarify the situation with bias in GAN loss functions raised by recent work: we show that gradient estimators used in the optimization process for both MMD GANs and Wasserstein GANs are unbiased, but learning a discriminator based on samples leads to biased gradients for the generator parameters. We also discuss the issue of kernel choice for the MMD critic, and characterize the kernel corresponding to the energy distance used for the Cramer GAN critic. Being an integral probability metric, the MMD benefits from training strategies recently developed for Wasserstein GANs. In experiments, the MMD GAN is able to employ a smaller critic network than the Wasserstein GAN, resulting in a simpler and faster-training algorithm with matching performance. We also propose an improved measure of GAN convergence, the Kernel Inception Distance, and show how to use it to dynamically adapt learning rates during GAN training.

Key facts. Cited by 1,268 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 113; 2022: 129; 2023: 212; 2024: 299; 2025: 280; 2026: 234.

1,268 papers.

Sort:

By area:

  1. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  2. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  3. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  4. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,099
  5. 2022Denoising Diffusion Restoration Modelscited by 951
  6. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  7. 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 579
  8. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  9. 2021MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontierscited by 466
  10. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  11. 2023ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generationcited by 414
  12. 2023Analyzing and Improving the Training Dynamics of Diffusion Modelscited by 396
38 more
  1. 2023Ablating Concepts in Text-to-Image Diffusion Modelscited by 312
  2. 2022Perception Prioritized Training of Diffusion Modelscited by 301
  3. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  4. 2022Cold Diffusion: Inverting Arbitrary Image Transforms Without Noisecited by 275
  5. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 273
  6. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 251
  7. 2021Deblurring via Stochastic Refinementcited by 248
  8. 2022Transformers in Medical Imaging: A Surveycited by 245
  9. 2023Text2Tex: Text-driven Texture Synthesis via Diffusion Modelscited by 234
  10. 2021Large Scale Image Completion via Co-Modulated Generative Adversarial Networkscited by 219
  11. 2023A Variational Perspective on Solving Inverse Problems with Diffusion Modelscited by 217
  12. 2021GRAM: Generative Radiance Manifolds for 3D-Aware Image Generationcited by 216
  13. 2024FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Modelscited by 214
  14. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 211
  15. 2021Projected GANs Converge Fastercited by 204
  16. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusioncited by 204
  17. 2024BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusioncited by 200
  18. 2023Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion modelscited by 199
  19. 2022Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Qualitycited by 181
  20. 2021InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Renderingcited by 180
  21. 2023Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstructioncited by 180
  22. 2023StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-Oncited by 173
  23. 2022EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equationscited by 172
  24. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 164
  25. 2023Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigationcited by 162
  26. 2022Dress Code: High-Resolution Multi-Category Virtual Try-Oncited by 161
  27. 2021Neural SDEs as Infinite-Dimensional GANscited by 159
  28. 2023DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesiscited by 159
  29. 2021EditGAN: High-Precision Semantic Image Editingcited by 156
  30. 2023Manifold Preserving Guided Diffusioncited by 153
  31. 2021StyleSwin: Transformer-based GAN for High-resolution Image Generationcited by 152
  32. 2023LaDI-VTON: Latent Diffusion Textual-Inversion Enhanced Virtual Try-Oncited by 151
  33. 2024OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-oncited by 150
  34. 2021CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesiscited by 149
  35. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  36. 2024MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captionscited by 144
  37. 2023AGIQA-3K: An Open Database for AI-Generated Image Quality Assessmentcited by 142
  38. 2022The Devil Is in the Details: Window-based Attention for Image Compressioncited by 141

50 most cited of 1,268 All 1,268 (JSON)