# Improving the Speed and Quality of GAN by Adversarial Training

arXiv: https://arxiv.org/abs/2008.03364 · HTML: https://mlsanity.com/paper/2008.03364/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Aug 2020.

## Built on by (most cited first, 6 of 6)

- [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)
- [Improving GAN Training via Feature Space Shrinkage](https://mlsanity.com/paper/2303.01559/) (2023)
- [3D GANs and Latent Space: A comprehensive survey](https://mlsanity.com/paper/2304.03932/) (2023)
- [Is Certifying ℓp Robustness Still Worthwhile?](https://mlsanity.com/paper/2310.09361/) (2023)
- [Accelerating Inference of Discrete Autoregressive Normalizing Flows by Selective Jacobi Decoding](https://mlsanity.com/paper/2505.24791/) (2025)

## Abstract (arXiv)

Generative adversarial networks (GAN) have shown remarkable results in image generation tasks. High fidelity class-conditional GAN methods often rely on stabilization techniques by constraining the global Lipschitz continuity. Such regularization leads to less expressive models and slower convergence speed; other techniques, such as the large batch training, require unconventional computing power and are not widely accessible. In this paper, we develop an efficient algorithm, namely FastGAN (Free AdverSarial Training), to improve the speed and quality of GAN training based on the adversarial training technique. We benchmark our method on CIFAR10, a subset of ImageNet, and the full ImageNet datasets. We choose strong baselines such as SNGAN and SAGAN; the results demonstrate that our training algorithm can achieve better generation quality (in terms of the Inception score and Frechet Inception distance) with less overall training time. Most notably, our training algorithm brings ImageNet training to the broader public by requiring 2-4 GPUs.