mlsanityData to 7 Oct 2026

Are GANs Created Equal? A Large-Scale Study

arXiv 1711.10337 ↗First posted 28 Nov 2017stat.ML cs.LGcited by 267

Not on the map. Why?

Cited by 27 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Generative adversarial networks (GAN) are a powerful subclass of generative models. Despite a very rich research activity leading to numerous interesting GAN algorithms, it is still very hard to assess which algorithm(s) perform better than others. We conduct a neutral, multi-faceted large-scale empirical study on state-of-the art models and evaluation measures. We find that most models can reach similar scores with enough hyperparameter optimization and random restarts. This suggests that improvements can arise from a higher computational budget and tuning more than fundamental algorithmic changes. To overcome some limitations of the current metrics, we also propose several data sets on which precision and recall can be computed. Our experimental results suggest that future GAN research should be based on more systematic and objective evaluation procedures. Finally, we did not find evidence that any of the tested algorithms consistently outperforms the non-saturating GAN introduced in citegoodfellow2014generative.

Key facts. Cited by 267 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 3; 2019: 2; 2020: 1; 2021: 71; 2022: 53; 2023: 59; 2024: 27; 2025: 30; 2026: 21.

267 papers.

Sort:

By area:

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 781
  4. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 251
  5. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 211
  6. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learningcited by 203
  7. 2021Accounting for Variance in Machine Learning Benchmarkscited by 195
  8. 2021How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Modelscited by 193
  9. 2021IQ-Learn: Inverse soft-Q Learning for Imitationcited by 191
  10. 2021TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Upcited by 162
  11. 2022Earthformer: Exploring Space-Time Transformers for Earth System Forecastingcited by 146
  12. 2021Pros and Cons of GAN Evaluation Measures: New Developmentscited by 121
38 more
  1. 2021Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAEcited by 106
  2. 2021An Introduction to Deep Generative Modelingcited by 104
  3. 2018Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flowcited by 103
  4. 2021Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmarkcited by 95
  5. 2024Better than classical? The subtle art of benchmarking quantum machine learning modelscited by 82
  6. 2023Spontaneous Symmetry Breaking in Generative Diffusion Modelscited by 74
  7. 2025CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generationcited by 73
  8. 2021What Matters for Adversarial Imitation Learning?cited by 70
  9. 2022Synthetic Data -- what, why and how?cited by 66
  10. 2021GANs for Medical Image Synthesis: An Empirical Studycited by 64
  11. 2021DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Datacited by 62
  12. 2022What Makes Transfer Learning Work For Medical Images: Feature Reuse & Other Factorscited by 61
  13. 2021Sig-Wasserstein GANs for Time Series Generationcited by 60
  14. 2023Elo Uncovered: Robustness and Best Practices in Language Model Evaluationcited by 58
  15. 2021Randomness In Neural Network Training: Characterizing The Impact of Toolingcited by 57
  16. 2023Empirical Design in Reinforcement Learningcited by 54
  17. 2021On Aliased Resizing and Surprising Subtleties in GAN Evaluationcited by 51
  18. 2022ArtFID: Quantitative Evaluation of Neural Style Transfercited by 49
  19. 2023Vector Quantized Time Series Generation with a Bidirectional Prior Modelcited by 49
  20. 2023Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEscited by 48
  21. 2021Training GANs with Stronger Augmentations via Contrastive Discriminatorcited by 45
  22. 2022Reproducibility in Learningcited by 44
  23. 2022On Evaluation Metrics for Graph Generative Modelscited by 44
  24. 2019Random Expert Distillation: Imitation Learning via Expert Policy Support Estimationcited by 42
  25. 2024Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Seriescited by 42
  26. 2025Diffusion Models for Robotic Manipulation: A Surveycited by 39
  27. 2021Perceptual Learned Video Compression with Recurrent Conditional GANcited by 38
  28. 2022Quantized GAN for Complex Music Generation from Dance Videoscited by 37
  29. 2018Sample-Efficient Imitation Learning via Generative Adversarial Netscited by 36
  30. 2023Generative Sliced MMD Flows with Riesz Kernelscited by 36
  31. 2024StableIdentity: Inserting Anybody into Anywhere at First Sightcited by 35
  32. 2022When do GANs replicate? On the choice of dataset sizecited by 34
  33. 2025Harnessing Diffusion-Yielded Score Priors for Image Restorationcited by 34
  34. 2021Wasserstein GANs Work Because They Fail (to Approximate the Wasserstein Distance)cited by 33
  35. 2021High Perceptual Quality Image Denoising with a Posterior Sampling CGANcited by 33
  36. 2022Class-Aware Adversarial Transformers for Medical Image Segmentationcited by 33
  37. 2021SketchEdit: Mask-Free Local Image Manipulation with Partial Sketchescited by 32
  38. 2025Position: Model Collapse Does Not Mean What You Thinkcited by 32

50 most cited of 267 All 267 (JSON)