# DivAug: Plug-in Automated Data Augmentation with Explicit Diversity Maximization

arXiv: https://arxiv.org/abs/2103.14545 · HTML: https://mlsanity.com/paper/2103.14545/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 26 Mar 2021.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Fast AutoAugment](https://mlsanity.com/paper/1905.00397/) (2019)
- [Deep Pyramidal Residual Networks](https://mlsanity.com/paper/1610.02915/) (2016)
- [Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules](https://mlsanity.com/paper/1905.05393/) (2019)
- [Adversarial AutoAugment](https://mlsanity.com/paper/1912.11188/) (2019)
- [A Kernel Theory of Modern Data Augmentation](https://mlsanity.com/paper/1803.06084/) (2018)
- [Data Augmentation by Pairing Samples for Images Classification](https://mlsanity.com/paper/1801.02929/) (2018)
- [Faster AutoAugment: Learning Augmentation Strategies using Backpropagation](https://mlsanity.com/paper/1911.06987/) (2019)
- [Shake-Shake regularization](https://mlsanity.com/paper/1705.07485/) (2017)
- [Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence](https://mlsanity.com/paper/1905.13277/) (2019)
- [On the Generalization Effects of Linear Transformations in Data Augmentation](https://mlsanity.com/paper/2005.00695/) (2020)
- [Affinity and Diversity: Quantifying Mechanisms of Data Augmentation](https://mlsanity.com/paper/2002.08973/) (2020)
- [ShakeDrop Regularization for Deep Residual Learning](https://mlsanity.com/paper/1802.02375/) (2018)

## Built on by (most cited first, 15 of 15)

- [Large Language Models for Healthcare Data Augmentation: An Example on Patient-Trial Matching](https://mlsanity.com/paper/2303.16756/) (2023)
- [AADG: Automatic Augmentation for Domain Generalization on Retinal Image Segmentation](https://mlsanity.com/paper/2207.13249/) (2022)
- [Automated data processing and feature engineering for deep learning and big data applications: a survey](https://mlsanity.com/paper/2403.11395/) (2024)
- [RSC: Accelerating Graph Neural Networks Training via Randomized Sparse Computations](https://mlsanity.com/paper/2210.10737/) (2022)
- [Uncertainty-aware Unsupervised Multi-Object Tracking](https://mlsanity.com/paper/2307.15409/) (2023)
- [Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model](https://mlsanity.com/paper/2305.15265/) (2023)
- [Diversity-oriented Data Augmentation with Large Language Models](https://mlsanity.com/paper/2502.11671/) (2025)
- [Data Optimization in Deep Learning: A Survey](https://mlsanity.com/paper/2310.16499/) (2023)
- [Anchor Data Augmentation](https://mlsanity.com/paper/2311.06965/) (2023)
- [Universal Adaptive Data Augmentation](https://mlsanity.com/paper/2207.06658/) (2022)
- [Feature transforms for image data augmentation](https://mlsanity.com/paper/2201.09700/) (2022)
- [Empirical Evaluation of Data Augmentations for Biobehavioral Time Series Data with Deep Learning](https://mlsanity.com/paper/2210.06701/) (2022)
- [LatentAugment: Data Augmentation via Guided Manipulation of GAN's Latent Space](https://mlsanity.com/paper/2307.11375/) (2023)
- [Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods](https://mlsanity.com/paper/2403.08352/) (2024)
- [Ctrl-A: Control-Driven Online Data Augmentation](https://mlsanity.com/paper/2603.21819/) (2026)

## Abstract (arXiv)

Human-designed data augmentation strategies have been replaced by automatically learned augmentation policy in the past two years. Specifically, recent work has empirically shown that the superior performance of the automated data augmentation methods stems from increasing the diversity of augmented data citeautoaug, randaug. However, two factors regarding the diversity of augmented data are still missing: 1) the explicit definition (and thus measurement) of diversity and 2) the quantifiable relationship between diversity and its regularization effects. To bridge this gap, we propose a diversity measure called Variance Diversity and theoretically show that the regularization effect of data augmentation is promised by Variance Diversity. We validate in experiments that the relative gain from automated data augmentation in test accuracy is highly correlated to Variance Diversity. An unsupervised sampling-based framework, DivAug, is designed to directly maximize Variance Diversity and hence strengthen the regularization effect. Without requiring a separate search process, the performance gain from DivAug is comparable with the state-of-the-art method with better efficiency. Moreover, under the semi-supervised setting, our framework can further improve the performance of semi-supervised learning algorithms compared to RandAugment, making it highly applicable to real-world problems, where labeled data is scarce. The code is available at texttturlhttps://github.com/warai-0toko/DivAug.