# On Data Augmentation for GAN Training

arXiv: https://arxiv.org/abs/2006.05338 · HTML: https://mlsanity.com/paper/2006.05338/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2020.

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

- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Dataset Distillation by Matching Training Trajectories](https://mlsanity.com/paper/2203.11932/) (2022)
- [Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory](https://mlsanity.com/paper/2211.10586/) (2022)
- [Regularizing Generative Adversarial Networks under Limited Data](https://mlsanity.com/paper/2104.03310/) (2021)
- [DREAM: Efficient Dataset Distillation by Representative Matching](https://mlsanity.com/paper/2302.14416/) (2023)
- [Ensembling Off-the-shelf Models for GAN Training](https://mlsanity.com/paper/2112.09130/) (2021)
- [DC-BENCH: Dataset Condensation Benchmark](https://mlsanity.com/paper/2207.09639/) (2022)
- [Sketch Your Own GAN](https://mlsanity.com/paper/2108.02774/) (2021)
- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective](https://mlsanity.com/paper/2103.00397/) (2021)
- [Rewriting Geometric Rules of a GAN](https://mlsanity.com/paper/2207.14288/) (2022)
- [FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs](https://mlsanity.com/paper/2207.08630/) (2022)
- [CharacterGAN: Few-Shot Keypoint Character Animation and Reposing](https://mlsanity.com/paper/2102.03141/) (2021)
- [ReMix: Towards Image-to-Image Translation with Limited Data](https://mlsanity.com/paper/2103.16835/) (2021)
- [Self-Supervised GANs with Label Augmentation](https://mlsanity.com/paper/2106.08601/) (2021)
- [DREAM+: Efficient Dataset Distillation by Bidirectional Representative Matching](https://mlsanity.com/paper/2310.15052/) (2023)
- [Peer is Your Pillar: A Data-unbalanced Conditional GANs for Few-shot Image Generation](https://mlsanity.com/paper/2311.08217/) (2023)
- [PConv: Simple yet Effective Convolutional Layer for Generative Adversarial Network](https://mlsanity.com/paper/2101.10841/) (2021)
- [ScoreMix: A Scalable Augmentation Strategy for Training GANs with Limited Data](https://mlsanity.com/paper/2210.15137/) (2022)
- [Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variations](https://mlsanity.com/paper/2308.10554/) (2023)
- [MS3D: A RG Flow-Based Regularization for GAN Training with Limited Data](https://mlsanity.com/paper/2408.11135/) (2024)
- [Learning Spatially-Adaptive Squeeze-Excitation Networks for Image Synthesis and Image Recognition](https://mlsanity.com/paper/2112.14804/) (2021)
- [Looks Like Magic: Transfer Learning in GANs to Generate New Card Illustrations](https://mlsanity.com/paper/2205.14442/) (2022)
- [Texturize a GAN Using a Single Image](https://mlsanity.com/paper/2302.10600/) (2023)
- [Style Quantization for Data-Efficient GAN Training](https://mlsanity.com/paper/2503.24282/) (2025)

## Abstract (arXiv)

Recent successes in Generative Adversarial Networks (GAN) have affirmed the importance of using more data in GAN training. Yet it is expensive to collect data in many domains such as medical applications. Data Augmentation (DA) has been applied in these applications. In this work, we first argue that the classical DA approach could mislead the generator to learn the distribution of the augmented data, which could be different from that of the original data. We then propose a principled framework, termed Data Augmentation Optimized for GAN (DAG), to enable the use of augmented data in GAN training to improve the learning of the original distribution. We provide theoretical analysis to show that using our proposed DAG aligns with the original GAN in minimizing the Jensen-Shannon (JS) divergence between the original distribution and model distribution. Importantly, the proposed DAG effectively leverages the augmented data to improve the learning of discriminator and generator. We conduct experiments to apply DAG to different GAN models: unconditional GAN, conditional GAN, self-supervised GAN and CycleGAN using datasets of natural images and medical images. The results show that DAG achieves consistent and considerable improvements across these models. Furthermore, when DAG is used in some GAN models, the system establishes state-of-the-art Frechet Inception Distance (FID) scores. Our code is available.