# Progressive Augmentation of GANs

arXiv: https://arxiv.org/abs/1901.10422 · HTML: https://mlsanity.com/paper/1901.10422/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jan 2019.

## Built on by (most cited first, 13 of 13)

- [StyleGAN-Human: A Data-Centric Odyssey of Human Generation](https://mlsanity.com/paper/2204.11823/) (2022)
- [Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation](https://mlsanity.com/paper/2106.06056/) (2021)
- [Existence and Estimation of Critical Batch Size for Training Generative Adversarial Networks with Two Time-Scale Update Rule](https://mlsanity.com/paper/2201.11989/) (2022)
- [MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains](https://mlsanity.com/paper/2104.13742/) (2021)
- [Towards Universal Texture Synthesis by Combining Texton Broadcasting with Noise Injection in StyleGAN-2](https://mlsanity.com/paper/2203.04221/) (2022)
- [Evaluating Post-Training Compression in GANs using Locality-Sensitive Hashing](https://mlsanity.com/paper/2103.11912/) (2021)
- [Generative Adversarial Networks via a Composite Annealing of Noise and Diffusion](https://mlsanity.com/paper/2105.00220/) (2021)
- [Foundations and Models in Modern Computer Vision: Key Building Blocks in Landmark Architectures](https://mlsanity.com/paper/2507.23357/) (2025)
- [Parameter and Data-Efficient Spectral StyleDCGAN](https://mlsanity.com/paper/2404.00597/) (2024)
- [Evaluation and Comparison of Emotionally Evocative Image Augmentation Methods](https://mlsanity.com/paper/2406.16187/) (2024)
- [Advances in Photoacoustic Imaging Reconstruction and Quantitative Analysis for Biomedical Applications](https://mlsanity.com/paper/2411.02843/) (2024)
- [A Turn Toward Better Alignment: Few-Shot Generative Adaptation with Equivariant Feature Rotation](https://mlsanity.com/paper/2512.21174/) (2025)
- [HP-GAN: Harnessing pretrained networks for GAN improvement with FakeTwins and discriminator consistency](https://mlsanity.com/paper/2602.03039/) (2026)

## Abstract (arXiv)

Training of Generative Adversarial Networks (GANs) is notoriously fragile, requiring to maintain a careful balance between the generator and the discriminator in order to perform well. To mitigate this issue we introduce a new regularization technique - progressive augmentation of GANs (PA-GAN). The key idea is to gradually increase the task difficulty of the discriminator by progressively augmenting its input or feature space, thus enabling continuous learning of the generator. We show that the proposed progressive augmentation preserves the original GAN objective, does not compromise the discriminator's optimality and encourages a healthy competition between the generator and discriminator, leading to the better-performing generator. We experimentally demonstrate the effectiveness of PA-GAN across different architectures and on multiple benchmarks for the image synthesis task, on average achieving ~3 point improvement of the FID score.