# Data Augmentation Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1711.04340 · HTML: https://mlsanity.com/paper/1711.04340/

## Key facts

- Cited by 278 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Nov 2017.

## Built on by (most cited first, 30 of 278)

- [Effective Data Augmentation With Diffusion Models](https://mlsanity.com/paper/2302.07944/) (2023)
- [Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection](https://mlsanity.com/paper/2203.12208/) (2022)
- [Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning](https://mlsanity.com/paper/2308.06038/) (2023)
- [Contrastive Learning with Stronger Augmentations](https://mlsanity.com/paper/2104.07713/) (2021)
- [On the Stability of Iterative Retraining of Generative Models on their own Data](https://mlsanity.com/paper/2310.00429/) (2023)
- [MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2103.12579/) (2021)
- [A Comprehensive Survey of Image Augmentation Techniques for Deep Learning](https://mlsanity.com/paper/2205.01491/) (2022)
- [Diffusion Model as Representation Learner](https://mlsanity.com/paper/2308.10916/) (2023)
- [Leaving Reality to Imagination: Robust Classification via Generated Datasets](https://mlsanity.com/paper/2302.02503/) (2023)
- [Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection](https://mlsanity.com/paper/2103.15158/) (2021)
- [Synthesizing Informative Training Samples with GAN](https://mlsanity.com/paper/2204.07513/) (2022)
- [Synthcity: facilitating innovative use cases of synthetic data in different data modalities](https://mlsanity.com/paper/2301.07573/) (2023)
- [Break-It-Fix-It: Unsupervised Learning for Program Repair](https://mlsanity.com/paper/2106.06600/) (2021)
- [FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models](https://mlsanity.com/paper/2310.15160/) (2023)
- [Will Large-scale Generative Models Corrupt Future Datasets?](https://mlsanity.com/paper/2211.08095/) (2022)
- [C-Mixup: Improving Generalization in Regression](https://mlsanity.com/paper/2210.05775/) (2022)
- [Local Augmentation for Graph Neural Networks](https://mlsanity.com/paper/2109.03856/) (2021)
- [Training on Thin Air: Improve Image Classification with Generated Data](https://mlsanity.com/paper/2305.15316/) (2023)
- [A Closer Look at Few-shot Image Generation](https://mlsanity.com/paper/2205.03805/) (2022)
- [Synthetic Datasets for Autonomous Driving: A Survey](https://mlsanity.com/paper/2304.12205/) (2023)
- [Negative Data Augmentation](https://mlsanity.com/paper/2102.05113/) (2021)
- [Generative Adversarial Symmetry Discovery](https://mlsanity.com/paper/2302.00236/) (2023)
- [Generating Representative Samples for Few-Shot Classification](https://mlsanity.com/paper/2205.02918/) (2022)
- [Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofing](https://mlsanity.com/paper/2203.12175/) (2022)
- [Visual Localization via Few-Shot Scene Region Classification](https://mlsanity.com/paper/2208.06933/) (2022)
- [Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification](https://mlsanity.com/paper/2111.06399/) (2021)
- [State-of-the-Art in the Architecture, Methods and Applications of StyleGAN](https://mlsanity.com/paper/2202.14020/) (2022)
- [Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model](https://mlsanity.com/paper/2403.19600/) (2024)
- [Featurized Density Ratio Estimation](https://mlsanity.com/paper/2107.02212/) (2021)
- [Simple and Effective Synthesis of Indoor 3D Scenes](https://mlsanity.com/paper/2204.02960/) (2022)

## Abstract (arXiv)

Effective training of neural networks requires much data. In the low-data regime, parameters are underdetermined, and learnt networks generalise poorly. Data Augmentation alleviates this by using existing data more effectively. However standard data augmentation produces only limited plausible alternative data. Given there is potential to generate a much broader set of augmentations, we design and train a generative model to do data augmentation. The model, based on image conditional Generative Adversarial Networks, takes data from a source domain and learns to take any data item and generalise it to generate other within-class data items. As this generative process does not depend on the classes themselves, it can be applied to novel unseen classes of data. We show that a Data Augmentation Generative Adversarial Network (DAGAN) augments standard vanilla classifiers well. We also show a DAGAN can enhance few-shot learning systems such as Matching Networks. We demonstrate these approaches on Omniglot, on EMNIST having learnt the DAGAN on Omniglot, and VGG-Face data. In our experiments we can see over 13% increase in accuracy in the low-data regime experiments in Omniglot (from 69% to 82%), EMNIST (73.9% to 76%) and VGG-Face (4.5% to 12%); in Matching Networks for Omniglot we observe an increase of 0.5% (from 96.9% to 97.4%) and an increase of 1.8% in EMNIST (from 59.5% to 61.3%).