# KeepAugment: A Simple Information-Preserving Data Augmentation Approach

arXiv: https://arxiv.org/abs/2011.11778 · HTML: https://mlsanity.com/paper/2011.11778/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2020.

## Built on by (most cited first, 30 of 52)

- [Image Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2204.08610/) (2022)
- [TransMix: Attend to Mix for Vision Transformers](https://mlsanity.com/paper/2111.09833/) (2021)
- [Survey: Image Mixing and Deleting for Data Augmentation](https://mlsanity.com/paper/2106.07085/) (2021)
- [A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning](https://mlsanity.com/paper/2210.04561/) (2022)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [LEMON: Lossless model expansion](https://mlsanity.com/paper/2310.07999/) (2023)
- [CutDepth:Edge-aware Data Augmentation in Depth Estimation](https://mlsanity.com/paper/2107.07684/) (2021)
- [IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers](https://mlsanity.com/paper/2310.04780/) (2023)
- [Automated data processing and feature engineering for deep learning and big data applications: a survey](https://mlsanity.com/paper/2403.11395/) (2024)
- [EntAugment: Entropy-Driven Adaptive Data Augmentation Framework for Image Classification](https://mlsanity.com/paper/2409.06290/) (2024)
- [SageMix: Saliency-Guided Mixup for Point Clouds](https://mlsanity.com/paper/2210.06944/) (2022)
- [Background-Mixed Augmentation for Weakly Supervised Change Detection](https://mlsanity.com/paper/2211.11478/) (2022)
- [Vulnerability-Aware Spatio-Temporal Learning for Generalizable Deepfake Video Detection](https://mlsanity.com/paper/2501.01184/) (2025)
- [Local Patch AutoAugment with Multi-Agent Collaboration](https://mlsanity.com/paper/2103.11099/) (2021)
- [FrAug: Frequency Domain Augmentation for Time Series Forecasting](https://mlsanity.com/paper/2302.09292/) (2023)
- [AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classification](https://mlsanity.com/paper/2211.16040/) (2022)
- [AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentation](https://mlsanity.com/paper/2405.11467/) (2024)
- [Adversarial Counterfactual Augmentation: Application in Alzheimer's Disease Classification](https://mlsanity.com/paper/2203.07815/) (2022)
- [SAGE: Saliency-Guided Mixup with Optimal Rearrangements](https://mlsanity.com/paper/2211.00113/) (2022)
- [When Dynamic Data Selection Meets Data Augmentation](https://mlsanity.com/paper/2505.03809/) (2025)
- [A knowledge-driven vowel-based approach of depression classification from speech using data augmentation](https://mlsanity.com/paper/2210.15261/) (2022)
- [Domain Generalization by Rejecting Extreme Augmentations](https://mlsanity.com/paper/2310.06670/) (2023)
- [SimPSI: A Simple Strategy to Preserve Spectral Information in Time Series Data Augmentation](https://mlsanity.com/paper/2312.05790/) (2023)
- [ReSmooth: Detecting and Utilizing OOD Samples when Training with Data Augmentation](https://mlsanity.com/paper/2205.12606/) (2022)
- [Mixing Data Augmentation with Preserving Foreground Regions in Medical Image Segmentation](https://mlsanity.com/paper/2304.13490/) (2023)
- [KeepOriginalAugment: Single Image-based Better Information-Preserving Data Augmentation Approach](https://mlsanity.com/paper/2405.06354/) (2024)
- [ImportantAug: a data augmentation agent for speech](https://mlsanity.com/paper/2112.07156/) (2021)
- [Hint-Aug: Drawing Hints from Foundation Vision Transformers Towards Boosted Few-Shot Parameter-Efficient Tuning](https://mlsanity.com/paper/2304.12520/) (2023)
- [The Overfocusing Bias of Convolutional Neural Networks: A Saliency-Guided Regularization Approach](https://mlsanity.com/paper/2409.17370/) (2024)
- [Robust and Explainable Depression Identification from Speech Using Vowel-Based Ensemble Learning Approaches](https://mlsanity.com/paper/2410.18298/) (2024)

## Abstract (arXiv)

Data augmentation (DA) is an essential technique for training state-of-the-art deep learning systems. In this paper, we empirically show data augmentation might introduce noisy augmented examples and consequently hurt the performance on unaugmented data during inference. To alleviate this issue, we propose a simple yet highly effective approach, dubbed KeepAugment, to increase augmented images fidelity. The idea is first to use the saliency map to detect important regions on the original images and then preserve these informative regions during augmentation. This information-preserving strategy allows us to generate more faithful training examples. Empirically, we demonstrate our method significantly improves on a number of prior art data augmentation schemes, e.g. AutoAugment, Cutout, random erasing, achieving promising results on image classification, semi-supervised image classification, multi-view multi-camera tracking and object detection.