# Deep AutoAugment

arXiv: https://arxiv.org/abs/2203.06172 · HTML: https://mlsanity.com/paper/2203.06172/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 32 references that are in the map.
- First posted on arXiv 11 Mar 2022.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [ResNet strikes back: An improved training procedure in timm](https://mlsanity.com/paper/2110.00476/) (2021)
- [Fast AutoAugment](https://mlsanity.com/paper/1905.00397/) (2019)
- [TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation](https://mlsanity.com/paper/2103.10158/) (2021)
- [Improve Unsupervised Domain Adaptation with Mixup Training](https://mlsanity.com/paper/2001.00677/) (2020)
- [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)
- [Adapting Auxiliary Losses Using Gradient Similarity](https://mlsanity.com/paper/1812.02224/) (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)
- [MultiGrain: a unified image embedding for classes and instances](https://mlsanity.com/paper/1902.05509/) (2019)
- [Optimizing Data Usage via Differentiable Rewards](https://mlsanity.com/paper/1911.10088/) (2019)
- [UniformAugment: A Search-free Probabilistic Data Augmentation Approach](https://mlsanity.com/paper/2003.14348/) (2020)
- [Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error](https://mlsanity.com/paper/2105.13343/) (2021)
- [Direct Differentiable Augmentation Search](https://mlsanity.com/paper/2104.04282/) (2021)
- [In-Loop Meta-Learning with Gradient-Alignment Reward](https://mlsanity.com/paper/2102.03275/) (2021)

## Built on by (most cited first, 18 of 18)

- [SF(DA)2: Source-free Domain Adaptation Through the Lens of Data Augmentation](https://mlsanity.com/paper/2403.10834/) (2024)
- [Automatic Data Augmentation via Invariance-Constrained Learning](https://mlsanity.com/paper/2209.15031/) (2022)
- [Learning Instance-Specific Augmentations by Capturing Local Invariances](https://mlsanity.com/paper/2206.00051/) (2022)
- [Automated data processing and feature engineering for deep learning and big data applications: a survey](https://mlsanity.com/paper/2403.11395/) (2024)
- [When to Learn What: Model-Adaptive Data Augmentation Curriculum](https://mlsanity.com/paper/2309.04747/) (2023)
- [Understanding the Detrimental Class-level Effects of Data Augmentation](https://mlsanity.com/paper/2401.01764/) (2023)
- [RangeAugment: Efficient Online Augmentation with Range Learning](https://mlsanity.com/paper/2212.10553/) (2022)
- [Data Augmentation Policy Search for Long-Term Forecasting](https://mlsanity.com/paper/2405.00319/) (2024)
- [Data Augmentation for Neural NLP](https://mlsanity.com/paper/2302.11412/) (2023)
- [LatentAugment: Dynamically Optimized Latent Probabilities of Data Augmentation](https://mlsanity.com/paper/2305.02668/) (2023)
- [Integrating GAN and Texture Synthesis for Enhanced Road Damage Detection](https://mlsanity.com/paper/2309.06747/) (2023)
- [Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods](https://mlsanity.com/paper/2403.08352/) (2024)
- [Optimizing Data Augmentation through Bayesian Model Selection](https://mlsanity.com/paper/2505.21813/) (2025)
- [One Model, Many Behaviors: Training-Induced Effects on Out-of-Distribution Detection](https://mlsanity.com/paper/2601.10836/) (2026)
- [Expeditious Saliency-guided Mix-up through Random Gradient Thresholding](https://mlsanity.com/paper/2212.04875/) (2022)
- [Unsupervised augmentation optimization for few-shot medical image segmentation](https://mlsanity.com/paper/2306.05107/) (2023)
- [Boosting Semi-Supervised 2D Human Pose Estimation by Revisiting Data Augmentation and Consistency Training](https://mlsanity.com/paper/2402.11566/) (2024)
- [Ctrl-A: Control-Driven Online Data Augmentation](https://mlsanity.com/paper/2603.21819/) (2026)

## Abstract (arXiv)

While recent automated data augmentation methods lead to state-of-the-art results, their design spaces and the derived data augmentation strategies still incorporate strong human priors. In this work, instead of fixing a set of hand-picked default augmentations alongside the searched data augmentations, we propose a fully automated approach for data augmentation search named Deep AutoAugment (DeepAA). DeepAA progressively builds a multi-layer data augmentation pipeline from scratch by stacking augmentation layers one at a time until reaching convergence. For each augmentation layer, the policy is optimized to maximize the cosine similarity between the gradients of the original and augmented data along the direction with low variance. Our experiments show that even without default augmentations, we can learn an augmentation policy that achieves strong performance with that of previous works. Extensive ablation studies show that the regularized gradient matching is an effective search method for data augmentation policies. Our code is available at: https://github.com/MSU-MLSys-Lab/DeepAA .