mlsanityData to 14 Oct 2026

Improved Precision and Recall Metric for Assessing Generative Models

arXiv 1904.06991 ↗First posted 15 Apr 2019stat.ML cs.LG cs.NEcited by 944

Not on the map. Why?

Cited by 442 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The ability to automatically estimate the quality and coverage of the samples produced by a generative model is a vital requirement for driving algorithm research. We present an evaluation metric that can separately and reliably measure both of these aspects in image generation tasks by forming explicit, non-parametric representations of the manifolds of real and generated data. We demonstrate the effectiveness of our metric in StyleGAN and BigGAN by providing several illustrative examples where existing metrics yield uninformative or contradictory results. Furthermore, we analyze multiple design variants of StyleGAN to better understand the relationships between the model architecture, training methods, and the properties of the resulting sample distribution. In the process, we identify new variants that improve the state-of-the-art. We also perform the first principled analysis of truncation methods and identify an improved method. Finally, we extend our metric to estimate the perceptual quality of individual samples, and use this to study latent space interpolations.

Key facts. Cited by 944 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 55; 2022: 97; 2023: 142; 2024: 196; 2025: 215; 2026: 239.

944 papers.

Sort:

By area:

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  3. 2022Scalable Diffusion Models with Transformerscited by 6,054
  4. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  5. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  6. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  7. 2023Consistency Modelscited by 1,822
  8. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
  9. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 777
  10. 2022On Distillation of Guided Diffusion Modelscited by 725
  11. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 703
  12. 2022Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learningcited by 561
38 more
  1. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 516
  2. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 502
  3. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 492
  4. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  5. 2021MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontierscited by 470
  6. 2023Improved Techniques for Training Consistency Modelscited by 439
  7. 2023Analyzing and Improving the Training Dynamics of Diffusion Modelscited by 402
  8. 2023DeepCache: Accelerating Diffusion Models for Freecited by 359
  9. 2022The Vendi Score: A Diversity Evaluation Metric for Machine Learningcited by 311
  10. 2024Guiding a Diffusion Model with a Bad Version of Itselfcited by 299
  11. 2025Diffusion Transformers with Representation Autoencoderscited by 295
  12. 2021Generating Images with Sparse Representationscited by 266
  13. 2023MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizercited by 262
  14. 2024Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Modelscited by 254
  15. 2023Self-Consuming Generative Models Go MADcited by 250
  16. 2025REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformerscited by 225
  17. 2021Large Scale Image Completion via Co-Modulated Generative Adversarial Networkscited by 220
  18. 2024Deep Compression Autoencoder for Efficient High-Resolution Diffusion Modelscited by 217
  19. 2024Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generationcited by 214
  20. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 213
  21. 2021Projected GANs Converge Fastercited by 208
  22. 2022Diffusion-GAN: Training GANs with Diffusioncited by 205
  23. 2023Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion modelscited by 205
  24. 2023VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluationcited by 201
  25. 2021How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Modelscited by 196
  26. 2023Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Modelscited by 177
  27. 2023Fast Training of Diffusion Models with Masked Transformerscited by 176
  28. 2022Fast Sampling of Diffusion Models via Operator Learningcited by 175
  29. 2023Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examplescited by 167
  30. 2023DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesiscited by 166
  31. 2022RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generationcited by 162
  32. 2023Flow Matching in Latent Spacecited by 160
  33. 2023Holistic Evaluation of Text-To-Image Modelscited by 160
  34. 2024Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generationcited by 155
  35. 2022Improving Sample Quality of Diffusion Models Using Self-Attention Guidancecited by 154
  36. 2024Learning-to-Cache: Accelerating Diffusion Transformer via Layer Cachingcited by 142
  37. 2024Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformerscited by 137
  38. 2023Similarity of Neural Network Models: A Survey of Functional and Representational Measurescited by 131

50 most cited of 944 All 944 (JSON)