# SODA: Self-organizing data augmentation in deep neural networks -- Application to biomedical image segmentation tasks

arXiv: https://arxiv.org/abs/2202.03223 · HTML: https://mlsanity.com/paper/2202.03223/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 7 Feb 2022.

## Builds on (most cited first, 8 of 8)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Effectiveness of Data Augmentation in Image Classification using Deep Learning](https://mlsanity.com/paper/1712.04621/) (2017)
- [Synthetic Data Augmentation using GAN for Improved Liver Lesion Classification](https://mlsanity.com/paper/1801.02385/) (2018)
- [Data Augmentation by Pairing Samples for Images Classification](https://mlsanity.com/paper/1801.02929/) (2018)
- [Style Augmentation: Data Augmentation via Style Randomization](https://mlsanity.com/paper/1809.05375/) (2018)
- [Direct Differentiable Augmentation Search](https://mlsanity.com/paper/2104.04282/) (2021)
- [Data Augmentation in Emotion Classification Using Generative Adversarial Networks](https://mlsanity.com/paper/1711.00648/) (2017)
- [An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization](https://mlsanity.com/paper/2007.05670/) (2020)

## Abstract (arXiv)

In practice, data augmentation is assigned a predefined budget in terms of newly created samples per epoch. When using several types of data augmentation, the budget is usually uniformly distributed over the set of augmentations but one can wonder if this budget should not be allocated to each type in a more efficient way. This paper leverages online learning to allocate on the fly this budget as part of neural network training. This meta-algorithm can be run at almost no extra cost as it exploits gradient based signals to determine which type of data augmentation should be preferred. Experiments suggest that this strategy can save computation time and thus goes in the way of greener machine learning practices.