mlsanityData to 7 Oct 2026

How good is my GAN?

arXiv 1807.09499 ↗First posted 25 Jul 2018cs.CV cs.LGcited by 74

Not on the map. Why?

Abstract (arXiv)

Generative adversarial networks (GANs) are one of the most popular methods for generating images today. While impressive results have been validated by visual inspection, a number of quantitative criteria have emerged only recently. We argue here that the existing ones are insufficient and need to be in adequation with the task at hand. In this paper we introduce two measures based on image classification---GAN-train and GAN-test, which approximate the recall (diversity) and precision (quality of the image) of GANs respectively. We evaluate a number of recent GAN approaches based on these two measures and demonstrate a clear difference in performance. Furthermore, we observe that the increasing difficulty of the dataset, from CIFAR10 over CIFAR100 to ImageNet, shows an inverse correlation with the quality of the GANs, as clearly evident from our measures.

Key facts. Cited by 74 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 17; 2023: 11; 2024: 13; 2025: 10; 2026: 3.

74 papers.

Sort:

By area:

  1. 2021Pros and Cons of GAN Evaluation Measures: New Developmentscited by 121
  2. 2024Understanding Hallucinations in Diffusion Models through Mode Interpolationcited by 87
  3. 2022PoseGPT: Quantization-based 3D Human Motion Generation and Forecastingcited by 78
  4. 2021GANs for Medical Image Synthesis: An Empirical Studycited by 64
  5. 2024SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?cited by 64
  6. 2022Adversarial random forests for density estimation and generative modelingcited by 44
  7. 2023Diffusion Models for Counterfactual Generation and Anomaly Detection in Brain Imagescited by 30
  8. 2021Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencodercited by 27
  9. 2022Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Casecited by 26
  10. 2023Toward Understanding Generative Data Augmentationcited by 25
  11. 2024A Simple Baseline for Spoken Language to Sign Language Translation with 3D Avatarscited by 18
  12. 2021Inverting Generative Adversarial Renderer for Face Reconstructioncited by 17
38 more
  1. 2021LARGE: Latent-Based Regression through GAN Semanticscited by 17
  2. 2024Unveiling Differences in Generative Models: A Scalable Differential Clustering Approachcited by 16
  3. 2021Generative Zero-shot Network Quantizationcited by 15
  4. 2021Semantic Palette: Guiding Scene Generation with Class Proportionscited by 14
  5. 2021Generative Modeling for Multi-task Visual Learningcited by 14
  6. 2022A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Trainingcited by 13
  7. 2021MoRe-Fi: Motion-robust and Fine-grained Respiration Monitoring via Deep-Learning UWB Radarcited by 11
  8. 2022On the Robustness of Quality Measures for GANscited by 11
  9. 2023Bridging the Gap: Enhancing the Utility of Synthetic Data via Post-Processing Techniquescited by 11
  10. 2021PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classificationcited by 10
  11. 2021Beta-VAE Reproducibility: Challenges and Extensionscited by 10
  12. 2021Exploring the Quality of GAN Generated Images for Person Re-Identificationcited by 9
  13. 2022RareGAN: Generating Samples for Rare Classescited by 9
  14. 2025AIM 2025 challenge on Inverse Tone Mapping Report: Methods and Resultscited by 8
  15. 2021TransferI2I: Transfer Learning for Image-to-Image Translation from Small Datasetscited by 7
  16. 2022Improved Input Reprogramming for GAN Conditioningcited by 7
  17. 2022FedSyn: Synthetic Data Generation using Federated Learningcited by 7
  18. 2024Leveraging Generative AI for Urban Digital Twins: A Scoping Review on the Autonomous Generation of Urban Data, Scenarios, Designs, and 3D City Models for Smart City Advancementcited by 7
  19. 2021Ensembles of GANs for synthetic training data generationcited by 6
  20. 2022Font Generation with Missing Impression Labelscited by 6
  21. 2022Generalizability of Adversarial Robustness Under Distribution Shiftscited by 6
  22. 2024Rethinking HTG Evaluation: Bridging Generation and Recognitioncited by 6
  23. 2023Regularizing Neural Networks with Meta-Learning Generative Modelscited by 5
  24. 2025Deterministic Image-to-Image Translation via Denoising Brownian Bridge Models with Dual Approximatorscited by 5
  25. 2023A Diffusion-based Method for Multi-turn Compositional Image Generationcited by 4
  26. 2024Bridging the Gap between Real-world and Synthetic Images for Testing Autonomous Driving Systemscited by 4
  27. 2025Data Can Speak for Itself: Quality-guided Utilization of Wireless Synthetic Datacited by 4
  28. 2021On The Distribution of Penultimate Activations of Classification Networkscited by 3
  29. 2022Reinforcing Generated Images via Meta-learning for One-Shot Fine-Grained Visual Recognitioncited by 3
  30. 2023Understanding Deep Generative Models with Generalized Empirical Likelihoodscited by 3
  31. 2024Synthetic Medical Imaging Generation with Generative Adversarial Networks For Plain Radiographscited by 3
  32. 2024Purposer: Putting Human Motion Generation in Contextcited by 3
  33. 2021H-GAN: the power of GANs in your Handscited by 2
  34. 2022Evaluating the Quality and Diversity of DCGAN-based Generatively Synthesized Diabetic Retinopathy Imagerycited by 2
  35. 2023Learning to Generate Training Datasets for Robust Semantic Segmentationcited by 2
  36. 2023Preserving Privacy in GANs Against Membership Inference Attackcited by 2
  37. 2024Modeling Eye Gaze Velocity Trajectories using GANs with Spectral Loss for Enhanced Fidelitycited by 2
  38. 2021Stein Latent Optimization for Generative Adversarial Networkscited by 1

50 most cited of 74 All 74 (JSON)