mlsanityData to 14 Oct 2026

Stabilizing Generative Adversarial Networks: A Survey

arXiv 1910.00927 ↗First posted 30 Sep 2019cs.LGcited by 57

Not on the map. Why?

Abstract (arXiv)

Generative Adversarial Networks (GANs) are a type of generative model which have received much attention due to their ability to model complex real-world data. Despite their recent successes, the process of training GANs remains challenging, suffering from instability problems such as non-convergence, vanishing or exploding gradients, and mode collapse. In recent years, a diverse set of approaches have been proposed which focus on stabilizing the GAN training procedure. The purpose of this survey is to provide a comprehensive overview of the GAN training stabilization methods which can be found in the literature. We discuss the advantages and disadvantages of each approach, offer a comparative summary, and conclude with a discussion of open problems.

Key facts. Cited by 57 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 9; 2022: 14; 2023: 8; 2024: 8; 2025: 16; 2026: 2.

57 papers.

Sort:

By area:

  1. 2022Diffusion Models for Medical Image Analysis: A Comprehensive Surveycited by 273
  2. 2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
  3. 2024Normalizing Flows are Capable Generative Modelscited by 91
  4. 2021AI-based Reconstruction for Fast MRI -- A Systematic Review and Meta-analysiscited by 38
  5. 2022A Survey on Training Challenges in Generative Adversarial Networks for Biomedical Image Analysiscited by 24
  6. 2022A survey on GANs for computer vision: Recent research, analysis and taxonomycited by 15
  7. 2021Inverse design optimization framework via a two-step deep learning approach: application to a wind turbine airfoilcited by 14
  8. 2024Deep learning for precipitation nowcasting: A survey from the perspective of time series forecastingcited by 14
  9. 2023Market-GAN: Adding Control to Financial Market Data Generation with Semantic Contextcited by 13
  10. 2022Time Series Generation with Masked Autoencodercited by 12
  11. 2022Autonomy and Intelligence in the Computing Continuum: Challenges, Enablers, and Future Directions for Orchestrationcited by 12
  12. 2021Realizing GANs via a Tunable Loss Functioncited by 10
38 more
  1. 2023Dynamic Flows on Curved Space Generated by Labeled Datacited by 10
  2. 2025An Optimisation Framework for Unsupervised Environment Designcited by 10
  3. 2022Interpretability Guarantees with Merlin-Arthur Classifierscited by 9
  4. 2025Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flowscited by 8
  5. 2022Quantifying Uncertainty In Traffic State Estimation Using Generative Adversarial Networkscited by 7
  6. 2022Minimax Optimality (Probably) Doesn't Imply Distribution Learning for GANscited by 6
  7. 2021HAD-Net: A Hierarchical Adversarial Knowledge Distillation Network for Improved Enhanced Tumour Segmentation Without Post-Contrast Imagescited by 5
  8. 2023Addressing GAN Training Instabilities via Tunable Classification Lossescited by 5
  9. 2024CT Synthesis with Conditional Diffusion Models for Abdominal Lymph Node Segmentationcited by 5
  10. 2025Learning Metal Microstructural Heterogeneity through Spatial Mapping of Diffraction Latent Space Featurescited by 5
  11. 2021DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Trainingcited by 4
  12. 2022Physics-Constrained Generative Adversarial Networks for 3D Turbulencecited by 4
  13. 2024Diffusion-Based Approaches in Medical Image Generation and Analysiscited by 4
  14. 2021Generative Adversarial Networks (GAN) Powered Fast Magnetic Resonance Imaging -- Mini Review, Comparison and Perspectivescited by 3
  15. 2022Generative Adversarial Networks for Image Augmentation in Agriculture: A Systematic Reviewcited by 3
  16. 2022Deep Reinforcement Learning for Multi-Agent Interactioncited by 3
  17. 2024Does Diffusion Beat GAN in Image Super Resolution?cited by 3
  18. 2024Data-Free Federated Class Incremental Learning with Diffusion-Based Generative Memorycited by 3
  19. 2024Generative Aerodynamic Design with Diffusion Probabilistic Modelscited by 3
  20. 2021Generative Adversarial Network: Some Analytical Perspectivescited by 2
  21. 2022DAG-WGAN: Causal Structure Learning With Wasserstein Generative Adversarial Networkscited by 2
  22. 2022Classical and learned MR to pseudo-CT mappings for accurate transcranial ultrasound simulationcited by 2
  23. 2023Standardized CycleGAN training for unsupervised stain adaptation in invasive carcinoma classification for breast histopathologycited by 2
  24. 2023(αD,αG)-GANs: Addressing GAN Training Instabilities via Dual Objectivescited by 2
  25. 2023Multilingual Multiword Expression Identification Using Lateral Inhibition and Domain Adaptationcited by 2
  26. 2025Adversarial Disentanglement by Backpropagation with Physics-Informed Variational Autoencodercited by 2
  27. 2025Guided Unconditional and Conditional Generative Models for Super-Resolution and Inference of Quasi-Geostrophic Turbulencecited by 2
  28. 2025An Encoder-Decoder Network for Beamforming over Sparse Large-Scale MIMO Channelscited by 2
  29. 2021GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networkscited by 1
  30. 2023Anomaly Detection in Aeronautics Data with Quantum-compatible Discrete Deep Generative Modelcited by 1
  31. 20233D GANs and Latent Space: A comprehensive surveycited by 1
  32. 2025Towards Scalable Topological Regularizerscited by 1
  33. 2025Controlling Ensemble Variance in Diffusion Models: An Application for Reanalyses Downscalingcited by 1
  34. 2025CloudBreaker: Breaking the Cloud Covers of Sentinel-2 Images using Multi-Stage Trained Conditional Flow Matching on Sentinel-1cited by 1
  35. 2025RoentMod: A Synthetic Chest X-Ray Modification Model to Identify and Correct Image Interpretation Model Shortcutscited by 1
  36. 2025A generative adversarial network optimization method for damage detection and digital twinning by deep AI fault learning: Z24 Bridge structural health monitoring benchmark validationcited by 1
  37. 2022Causality Learning With Wasserstein Generative Adversarial Networkscited by 0
  38. 2024Key-point Guided Deformable Image Manipulation Using Diffusion Modelcited by 0

50 most cited of 57 All 57 (JSON)