# UniformAugment: A Search-free Probabilistic Data Augmentation Approach

arXiv: https://arxiv.org/abs/2003.14348 · HTML: https://mlsanity.com/paper/2003.14348/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2020.

## Built on by (most cited first, 30 of 38)

- [DeiT III: Revenge of the ViT](https://mlsanity.com/paper/2204.07118/) (2022)
- [TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation](https://mlsanity.com/paper/2103.10158/) (2021)
- [SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation](https://mlsanity.com/paper/2312.04913/) (2023)
- [TeachAugment: Data Augmentation Optimization Using Teacher Knowledge](https://mlsanity.com/paper/2202.12513/) (2022)
- [Deep AutoAugment](https://mlsanity.com/paper/2203.06172/) (2022)
- [Automatic Data Augmentation via Invariance-Constrained Learning](https://mlsanity.com/paper/2209.15031/) (2022)
- [Towards Data-Centric Face Anti-Spoofing: Improving Cross-domain Generalization via Physics-based Data Synthesis](https://mlsanity.com/paper/2409.03501/) (2024)
- [AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation](https://mlsanity.com/paper/2103.05863/) (2021)
- [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)
- [A Survey of Automated Data Augmentation Algorithms for Deep Learning-based Image Classification Tasks](https://mlsanity.com/paper/2206.06544/) (2022)
- [Directional Self-supervised Learning for Heavy Image Augmentations](https://mlsanity.com/paper/2110.13555/) (2021)
- [Exploring Temporally Dynamic Data Augmentation for Video Recognition](https://mlsanity.com/paper/2206.15015/) (2022)
- [RangeAugment: Efficient Online Augmentation with Range Learning](https://mlsanity.com/paper/2212.10553/) (2022)
- [Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning](https://mlsanity.com/paper/2305.16379/) (2023)
- [Stimulative Training++: Go Beyond The Performance Limits of Residual Networks](https://mlsanity.com/paper/2305.02507/) (2023)
- [SLACK: Stable Learning of Augmentations with Cold-start and KL regularization](https://mlsanity.com/paper/2306.09998/) (2023)
- [Anchor Data Augmentation](https://mlsanity.com/paper/2311.06965/) (2023)
- [Augment like there's no tomorrow: Consistently performing neural networks for medical imaging](https://mlsanity.com/paper/2206.15274/) (2022)
- [Universal Adaptive Data Augmentation](https://mlsanity.com/paper/2207.06658/) (2022)
- [Domain Generalization by Rejecting Extreme Augmentations](https://mlsanity.com/paper/2310.06670/) (2023)
- [Sample-aware RandAugment: Search-free Automatic Data Augmentation for Effective Image Recognition](https://mlsanity.com/paper/2508.08004/) (2025)
- [Spectral decoupling allows training transferable neural networks in medical imaging](https://mlsanity.com/paper/2103.17171/) (2021)
- [MedAugment: Universal Automatic Data Augmentation Plug-in for Medical Image Analysis](https://mlsanity.com/paper/2306.17466/) (2023)
- [FreeAugment: Data Augmentation Search Across All Degrees of Freedom](https://mlsanity.com/paper/2409.04820/) (2024)
- [NBBOX: Noisy Bounding Box Improves Remote Sensing Object Detection](https://mlsanity.com/paper/2409.09424/) (2024)
- [In-Loop Meta-Learning with Gradient-Alignment Reward](https://mlsanity.com/paper/2102.03275/) (2021)
- [On the Efficacy of Multi-scale Data Samplers for Vision Applications](https://mlsanity.com/paper/2309.04502/) (2023)
- [Integrating GAN and Texture Synthesis for Enhanced Road Damage Detection](https://mlsanity.com/paper/2309.06747/) (2023)
- [DualAug: Exploiting Additional Heavy Augmentation with OOD Data Rejection](https://mlsanity.com/paper/2310.08139/) (2023)

## Abstract (arXiv)

Augmenting training datasets has been shown to improve the learning effectiveness for several computer vision tasks. A good augmentation produces an augmented dataset that adds variability while retaining the statistical properties of the original dataset. Some techniques, such as AutoAugment and Fast AutoAugment, have introduced a search phase to find a set of suitable augmentation policies for a given model and dataset. This comes at the cost of great computational overhead, adding up to several thousand GPU hours. More recently RandAugment was proposed to substantially speedup the search phase by approximating the search space by a couple of hyperparameters, but still incurring non-negligible cost for tuning those. In this paper we show that, under the assumption that the augmentation space is approximately distribution invariant, a uniform sampling over the continuous space of augmentation transformations is sufficient to train highly effective models. Based on that result we propose UniformAugment, an automated data augmentation approach that completely avoids a search phase. In addition to discussing the theoretical underpinning supporting our approach, we also use the standard datasets, as well as established models for image classification, to show that UniformAugment's effectiveness is comparable to the aforementioned methods, while still being highly efficient by virtue of not requiring any search.