# Universal Adaptive Data Augmentation

arXiv: https://arxiv.org/abs/2207.06658 · HTML: https://mlsanity.com/paper/2207.06658/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 39 references that are in the map.
- First posted on arXiv 14 Jul 2022.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models](https://mlsanity.com/paper/1708.03999/) (2017)
- [Simple Black-box Adversarial Attacks](https://mlsanity.com/paper/1905.07121/) (2019)
- [Fast AutoAugment](https://mlsanity.com/paper/1905.00397/) (2019)
- [Kornia: an Open Source Differentiable Computer Vision Library for PyTorch](https://mlsanity.com/paper/1910.02190/) (2019)
- [TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation](https://mlsanity.com/paper/2103.10158/) (2021)
- [Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules](https://mlsanity.com/paper/1905.05393/) (2019)
- [Receptive Field Block Net for Accurate and Fast Object Detection](https://mlsanity.com/paper/1711.07767/) (2017)
- [Adversarial AutoAugment](https://mlsanity.com/paper/1912.11188/) (2019)
- [Faster AutoAugment: Learning Augmentation Strategies using Backpropagation](https://mlsanity.com/paper/1911.06987/) (2019)
- [Shake-Shake regularization](https://mlsanity.com/paper/1705.07485/) (2017)
- [On the Generalization Effects of Linear Transformations in Data Augmentation](https://mlsanity.com/paper/2005.00695/) (2020)
- [Online Hyper-parameter Learning for Auto-Augmentation Strategy](https://mlsanity.com/paper/1905.07373/) (2019)
- [UniformAugment: A Search-free Probabilistic Data Augmentation Approach](https://mlsanity.com/paper/2003.14348/) (2020)
- [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)
- [Self-supervised Label Augmentation via Input Transformations](https://mlsanity.com/paper/1910.05872/) (2019)
- [DivAug: Plug-in Automated Data Augmentation with Explicit Diversity Maximization](https://mlsanity.com/paper/2103.14545/) (2021)

## Built on by (most cited first, 5 of 5)

- [Domain Generalization via Balancing Training Difficulty and Model Capability](https://mlsanity.com/paper/2309.00844/) (2023)
- [Boosting Model Resilience via Implicit Adversarial Data Augmentation](https://mlsanity.com/paper/2404.16307/) (2024)
- [AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentation](https://mlsanity.com/paper/2405.11467/) (2024)
- [Anchor Data Augmentation](https://mlsanity.com/paper/2311.06965/) (2023)
- [Ctrl-A: Control-Driven Online Data Augmentation](https://mlsanity.com/paper/2603.21819/) (2026)

## Abstract (arXiv)

Existing automatic data augmentation (DA) methods either ignore updating DA's parameters according to the target model's state during training or adopt update strategies that are not effective enough. In this work, we design a novel data augmentation strategy called "Universal Adaptive Data Augmentation" (UADA). Different from existing methods, UADA would adaptively update DA's parameters according to the target model's gradient information during training: given a pre-defined set of DA operations, we randomly decide types and magnitudes of DA operations for every data batch during training, and adaptively update DA's parameters along the gradient direction of the loss concerning DA's parameters. In this way, UADA can increase the training loss of the target networks, and the target networks would learn features from harder samples to improve the generalization. Moreover, UADA is very general and can be utilized in numerous tasks, e.g., image classification, semantic segmentation and object detection. Extensive experiments with various models are conducted on CIFAR-10, CIFAR-100, ImageNet, tiny-ImageNet, Cityscapes, and VOC07+12 to prove the significant performance improvements brought by UADA.