# Enabling Data Diversity: Efficient Automatic Augmentation via Regularized Adversarial Training

arXiv: https://arxiv.org/abs/2103.16493 · HTML: https://mlsanity.com/paper/2103.16493/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 27 references that are in the map.
- First posted on arXiv 30 Mar 2021.

## Builds on (most cited first, 22 of 22)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation](https://mlsanity.com/paper/1809.10486/) (2018)
- [Adversarial Examples Improve Image Recognition](https://mlsanity.com/paper/1911.09665/) (2019)
- [Generating Adversarial Examples with Adversarial Networks](https://mlsanity.com/paper/1801.02610/) (2018)
- [Fast AutoAugment](https://mlsanity.com/paper/1905.00397/) (2019)
- [Adversarial Training and Robustness for Multiple Perturbations](https://mlsanity.com/paper/1904.13000/) (2019)
- [Data augmentation using learned transformations for one-shot medical image segmentation](https://mlsanity.com/paper/1902.09383/) (2019)
- [Semi-Supervised and Task-Driven Data Augmentation](https://mlsanity.com/paper/1902.05396/) (2019)
- [ADef: an Iterative Algorithm to Construct Adversarial Deformations](https://mlsanity.com/paper/1804.07729/) (2018)
- [FocusNet: Imbalanced Large and Small Organ Segmentation with an End-to-End Deep Neural Network for Head and Neck CT Images](https://mlsanity.com/paper/1907.12056/) (2019)
- [Generalizability vs. Robustness: Adversarial Examples for Medical Imaging](https://mlsanity.com/paper/1804.00504/) (2018)
- [Automatic Data Augmentation for 3D Medical Image Segmentation](https://mlsanity.com/paper/2010.11695/) (2020)
- [Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentation](https://mlsanity.com/paper/2006.05847/) (2020)

## Built on by (most cited first, 10 of 10)

- [Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation](https://mlsanity.com/paper/2306.02416/) (2023)
- [Enhancing MR Image Segmentation with Realistic Adversarial Data Augmentation](https://mlsanity.com/paper/2108.03429/) (2021)
- [Data Scarcity in Recommendation Systems: A Survey](https://mlsanity.com/paper/2312.10073/) (2023)
- [Automated data processing and feature engineering for deep learning and big data applications: a survey](https://mlsanity.com/paper/2403.11395/) (2024)
- [Adversarial Counterfactual Augmentation: Application in Alzheimer's Disease Classification](https://mlsanity.com/paper/2203.07815/) (2022)
- [ADASSM: Adversarial Data Augmentation in Statistical Shape Models From Images](https://mlsanity.com/paper/2307.03273/) (2023)
- [MGAug: Multimodal Geometric Augmentation in Latent Spaces of Image Deformations](https://mlsanity.com/paper/2312.13440/) (2023)
- [Synthetic Data Generation for Augmenting Small Samples](https://mlsanity.com/paper/2501.18741/) (2025)
- [Improvise, Adapt, Overcome -- Telescopic Adapters for Efficient Fine-tuning of Vision Language Models in Medical Imaging](https://mlsanity.com/paper/2512.13855/) (2025)
- [Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods](https://mlsanity.com/paper/2403.08352/) (2024)

## Abstract (arXiv)

Data augmentation has proved extremely useful by increasing training data variance to alleviate overfitting and improve deep neural networks' generalization performance. In medical image analysis, a well-designed augmentation policy usually requires much expert knowledge and is difficult to generalize to multiple tasks due to the vast discrepancies among pixel intensities, image appearances, and object shapes in different medical tasks. To automate medical data augmentation, we propose a regularized adversarial training framework via two min-max objectives and three differentiable augmentation models covering affine transformation, deformation, and appearance changes. Our method is more automatic and efficient than previous automatic augmentation methods, which still rely on pre-defined operations with human-specified ranges and costly bi-level optimization. Extensive experiments demonstrated that our approach, with less training overhead, achieves superior performance over state-of-the-art auto-augmentation methods on both tasks of 2D skin cancer classification and 3D organs-at-risk segmentation.