# Ctrl-A: Control-Driven Online Data Augmentation

arXiv: https://arxiv.org/abs/2603.21819 · HTML: https://mlsanity.com/paper/2603.21819/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 45 references that are in the map.
- First posted on arXiv 23 Mar 2026.

## Builds on (most cited first, 30 of 30)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [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)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [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)
- [Time Series Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2002.12478/) (2020)
- [Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules](https://mlsanity.com/paper/1905.05393/) (2019)
- [A Comprehensive Survey of Image Augmentation Techniques for Deep Learning](https://mlsanity.com/paper/2205.01491/) (2022)
- [Faster AutoAugment: Learning Augmentation Strategies using Backpropagation](https://mlsanity.com/paper/1911.06987/) (2019)
- [Shake-Shake regularization](https://mlsanity.com/paper/1705.07485/) (2017)
- [Online Hyper-parameter Learning for Auto-Augmentation Strategy](https://mlsanity.com/paper/1905.07373/) (2019)
- [OnlineAugment: Online Data Augmentation with Less Domain Knowledge](https://mlsanity.com/paper/2007.09271/) (2020)
- [Direct Differentiable Augmentation Search](https://mlsanity.com/paper/2104.04282/) (2021)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [Understanding Test-Time Augmentation](https://mlsanity.com/paper/2402.06892/) (2024)
- [RIC-CNN: Rotation-Invariant Coordinate Convolutional Neural Network](https://mlsanity.com/paper/2211.11812/) (2022)
- [MetaAugment: Sample-Aware Data Augmentation Policy Learning](https://mlsanity.com/paper/2012.12076/) (2020)
- [Deep AutoAugment](https://mlsanity.com/paper/2203.06172/) (2022)
- [Automatic Data Augmentation via Invariance-Constrained Learning](https://mlsanity.com/paper/2209.15031/) (2022)
- [94% on CIFAR-10 in 3.29 Seconds on a Single GPU](https://mlsanity.com/paper/2404.00498/) (2024)
- [DivAug: Plug-in Automated Data Augmentation with Explicit Diversity Maximization](https://mlsanity.com/paper/2103.14545/) (2021)
- [RangeAugment: Efficient Online Augmentation with Range Learning](https://mlsanity.com/paper/2212.10553/) (2022)
- [Universal Adaptive Data Augmentation](https://mlsanity.com/paper/2207.06658/) (2022)
- [A Generic Self-Supervised Framework of Learning Invariant Discriminative Features](https://mlsanity.com/paper/2202.06914/) (2022)
- [The SVHN Dataset Is Deceptive for Probabilistic Generative Models Due to a Distribution Mismatch](https://mlsanity.com/paper/2312.02168/) (2023)

## Abstract (arXiv)

We introduce ControlAugment (Ctrl-A), an automated data augmentation algorithm for image-vision tasks, which incorporates principles from control theory for online adjustment of augmentation strength distributions during model training. Ctrl-A eliminates the need for initialization of individual augmentation strengths. Instead, augmentation strength distributions are dynamically, and individually, adapted during training based on a control-loop architecture and what we define as relative operation response curves. Using an operation-dependent update procedure provides Ctrl-A with the potential to suppress augmentation styles that negatively impact model performance, alleviating the need for manually engineering augmentation policies for new image-vision tasks. Experiments on the CIFAR-10, CIFAR-100, and SVHN-core benchmark datasets using the common WideResNet-28-10 architecture demonstrate that Ctrl-A is highly competitive with existing state-of-the-art data augmentation strategies.