mlsanityData to 7 Oct 2026

DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Training

arXiv 2101.07524 ↗First posted 19 Jan 2021cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce DuelGAN, a generative adversarial network (GAN) solution to improve the stability of the generated samples and to mitigate mode collapse. Built upon the Vanilla GAN's two-player game between the discriminator D1 and the generator G, we introduce a peer discriminator D2 to the min-max game. Similar to previous work using two discriminators, the first role of both D1, D2 is to distinguish between generated samples and real ones, while the generator tries to generate high-quality samples which are able to fool both discriminators. Different from existing methods, we introduce another game between D1 and D2 to discourage their agreement and therefore increase the level of diversity of the generated samples. This property alleviates the issue of early mode collapse by preventing D1 and D2 from converging too fast. We provide theoretical analysis for the equilibrium of the min-max game formed among G, D1, D2. We offer convergence behavior of DuelGAN as well as stability of the min-max game. It's worth mentioning that DuelGAN operates in the unsupervised setting, and the duel between D1 and D2 does not need any label supervision. Experiments results on a synthetic dataset and on real-world image datasets (MNIST, Fashion MNIST, CIFAR-10, STL-10, CelebA, VGG, and FFHQ) demonstrate that DuelGAN outperforms competitive baseline work in generating diverse and high-quality samples, while only introduces negligible computation cost.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 50 of its 61 references that are in the map. First posted on arXiv 19 Jan 2021.

Builds on

50 of 61 references.

References · 50

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  3. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  4. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  5. 2016Improved Techniques for Training GANscited by 2,938
  6. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  7. 2017Improved Training of Wasserstein GANscited by 2,223
  8. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  9. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  10. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  11. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  12. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
38 more
  1. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  2. 2016Least Squares Generative Adversarial Networkscited by 1,000
  3. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 911
  4. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  5. 2017Wasserstein GANcited by 635
  6. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
  7. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 504
  8. 2016Generating Videos with Scene Dynamicscited by 376
  9. 2017Pose Guided Person Image Generationcited by 251
  10. 2016Unrolled Generative Adversarial Networkscited by 208
  11. 2020Learning with Instance-Dependent Label Noise: A Sample Sieve Approachcited by 158
  12. 2016Semantic Image Inpainting with Deep Generative Modelscited by 156
  13. 2019Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Ratescited by 142
  14. 2019Consistency Regularization for Generative Adversarial Networkscited by 134
  15. 2016Unsupervised Cross-Domain Image Generationcited by 125
  16. 2016Invertible Conditional GANs for image editingcited by 118
  17. 2019AutoGAN: Neural Architecture Search for Generative Adversarial Networkscited by 94
  18. 2017Generative Face Completioncited by 79
  19. 2020A Contrastive Learning Approach for Training Variational Autoencoder Priorscited by 65
  20. 2017GP-GAN: Towards Realistic High-Resolution Image Blendingcited by 64
  21. 2016Generative Multi-Adversarial Networkscited by 60
  22. 2017Multi-Agent Diverse Generative Adversarial Networkscited by 59
  23. 2019Stabilizing Generative Adversarial Networks: A Surveycited by 57
  24. 2017Dual Discriminator Generative Adversarial Netscited by 55
  25. 2017Face Aging With Conditional Generative Adversarial Networkscited by 51
  26. 2016Stacked Generative Adversarial Networkscited by 44
  27. 2020When Optimizing f-divergence is Robust with Label Noisecited by 44
  28. 2017Loss-Sensitive Generative Adversarial Networks on Lipschitz Densitiescited by 29
  29. 2017Towards the Automatic Anime Characters Creation with Generative Adversarial Networkscited by 29
  30. 2018On gradient regularizers for MMD GANscited by 28
  31. 2018Dist-GAN: An Improved GAN using Distance Constraintscited by 26
  32. 2019Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Gamecited by 25
  33. 2019Multi-objective training of Generative Adversarial Networks with multiple discriminatorscited by 24
  34. 2019Prescribed Generative Adversarial Networkscited by 23
  35. 2017TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Networkcited by 21
  36. 2019Latent Space Factorisation and Manipulation via Matrix Subspace Projectioncited by 9
  37. 2017Multi-Generator Generative Adversarial Netscited by 7
  38. 2020microbatchGAN: Stimulating Diversity with Multi-Adversarial Discriminationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 0; 2023: 0; 2024: 0; 2025: 2; 2026: 1.

4 papers.

  1. 2025OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Modelscited by 7
  2. 2021The Deep Generative Decoder: MAP estimation of representations improves modeling of single-cell RNA datacited by 2
  3. 2025Assessing the Distributional Fidelity of Synthetic Chest X-rays using the Embedded Characteristic Scorecited by 1
  4. 2026StatD2GAN: When Calibration Masks Generator Quality in Held-Out Evaluation of Synthetic Weather Sequencescited by 0