# Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Game

arXiv: https://arxiv.org/abs/1911.06997 · HTML: https://mlsanity.com/paper/1911.06997/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2019.

## Built on by (most cited first, 25 of 25)

- [Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models](https://mlsanity.com/paper/2103.04922/) (2021)
- [Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis](https://mlsanity.com/paper/2101.04775/) (2021)
- [A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection](https://mlsanity.com/paper/2103.17195/) (2021)
- [Data-Efficient Instance Generation from Instance Discrimination](https://mlsanity.com/paper/2106.04566/) (2021)
- [Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling](https://mlsanity.com/paper/2510.01329/) (2025)
- [Measuring Fairness in Generative Models](https://mlsanity.com/paper/2107.07754/) (2021)
- [Discovering Transferable Forensic Features for CNN-generated Images Detection](https://mlsanity.com/paper/2208.11342/) (2022)
- [Improving GANs with A Dynamic Discriminator](https://mlsanity.com/paper/2209.09897/) (2022)
- [Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking](https://mlsanity.com/paper/2505.18495/) (2025)
- [Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise](https://mlsanity.com/paper/2206.01095/) (2022)
- [Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks](https://mlsanity.com/paper/2102.12033/) (2021)
- [Self-Supervised GANs with Label Augmentation](https://mlsanity.com/paper/2106.08601/) (2021)
- [Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach](https://mlsanity.com/paper/2104.04886/) (2021)
- [Augmentation-Aware Self-Supervision for Data-Efficient GAN Training](https://mlsanity.com/paper/2205.15677/) (2022)
- [Game of GANs: Game-Theoretical Models for Generative Adversarial Networks](https://mlsanity.com/paper/2106.06976/) (2021)
- [DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Training](https://mlsanity.com/paper/2101.07524/) (2021)
- [EXoN: EXplainable encoder Network](https://mlsanity.com/paper/2105.10867/) (2021)
- [Generative Adversarial Networks for Brain Images Synthesis: A Review](https://mlsanity.com/paper/2305.15421/) (2023)
- [Overcoming Mode Collapse with Adaptive Multi Adversarial Training](https://mlsanity.com/paper/2112.14406/) (2021)
- [Dynamically Masked Discriminator for Generative Adversarial Networks](https://mlsanity.com/paper/2306.07716/) (2023)
- [A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention](https://mlsanity.com/paper/2106.09914/) (2021)
- [SS-CPGAN: Self-Supervised Cut-and-Pasting Generative Adversarial Network for Object Segmentation](https://mlsanity.com/paper/2301.00366/) (2023)
- [Binary Hypothesis Testing for Softmax Models and Leverage Score Models](https://mlsanity.com/paper/2405.06003/) (2024)
- [Improved Image Generation via Sparse Modeling](https://mlsanity.com/paper/2104.00464/) (2021)
- [HP-GAN: Harnessing pretrained networks for GAN improvement with FakeTwins and discriminator consistency](https://mlsanity.com/paper/2602.03039/) (2026)

## Abstract (arXiv)

Self-supervised (SS) learning is a powerful approach for representation learning using unlabeled data. Recently, it has been applied to Generative Adversarial Networks (GAN) training. Specifically, SS tasks were proposed to address the catastrophic forgetting issue in the GAN discriminator. In this work, we perform an in-depth analysis to understand how SS tasks interact with learning of generator. From the analysis, we identify issues of SS tasks which allow a severely mode-collapsed generator to excel the SS tasks. To address the issues, we propose new SS tasks based on a multi-class minimax game. The competition between our proposed SS tasks in the game encourages the generator to learn the data distribution and generate diverse samples. We provide both theoretical and empirical analysis to support that our proposed SS tasks have better convergence property. We conduct experiments to incorporate our proposed SS tasks into two different GAN baseline models. Our approach establishes state-of-the-art FID scores on CIFAR-10, CIFAR-100, STL-10, CelebA, Imagenet 32×32 and Stacked-MNIST datasets, outperforming existing works by considerable margins in some cases. Our unconditional GAN model approaches performance of conditional GAN without using labeled data. Our code: https://github.com/tntrung/msgan