# DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Training

arXiv: https://arxiv.org/abs/2101.07524 · HTML: https://mlsanity.com/paper/2101.07524/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 61 references that are in the map.
- First posted on arXiv 19 Jan 2021.

## Builds on (most cited first, 30 of 50)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.03242/) (2016)
- [f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization](https://mlsanity.com/paper/1606.00709/) (2016)
- [Generating Videos with Scene Dynamics](https://mlsanity.com/paper/1609.02612/) (2016)
- [Pose Guided Person Image Generation](https://mlsanity.com/paper/1705.09368/) (2017)
- [Unrolled Generative Adversarial Networks](https://mlsanity.com/paper/1611.02163/) (2016)
- [Learning with Instance-Dependent Label Noise: A Sample Sieve Approach](https://mlsanity.com/paper/2010.02347/) (2020)
- [Semantic Image Inpainting with Deep Generative Models](https://mlsanity.com/paper/1607.07539/) (2016)
- [Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates](https://mlsanity.com/paper/1910.03231/) (2019)
- [Consistency Regularization for Generative Adversarial Networks](https://mlsanity.com/paper/1910.12027/) (2019)
- [Unsupervised Cross-Domain Image Generation](https://mlsanity.com/paper/1611.02200/) (2016)
- [Invertible Conditional GANs for image editing](https://mlsanity.com/paper/1611.06355/) (2016)
- [AutoGAN: Neural Architecture Search for Generative Adversarial Networks](https://mlsanity.com/paper/1908.03835/) (2019)
- [Generative Face Completion](https://mlsanity.com/paper/1704.05838/) (2017)

## Built on by (most cited first, 4 of 4)

- [OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models](https://mlsanity.com/paper/2510.22535/) (2025)
- [The Deep Generative Decoder: MAP estimation of representations improves modeling of single-cell RNA data](https://mlsanity.com/paper/2110.06672/) (2021)
- [Assessing the Distributional Fidelity of Synthetic Chest X-rays using the Embedded Characteristic Score](https://mlsanity.com/paper/2501.00744/) (2025)
- [StatD2GAN: When Calibration Masks Generator Quality in Held-Out Evaluation of Synthetic Weather Sequences](https://mlsanity.com/paper/2609.33761/) (2026)

## 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.