# The Effectiveness of Data Augmentation in Image Classification using Deep Learning

arXiv: https://arxiv.org/abs/1712.04621 · HTML: https://mlsanity.com/paper/1712.04621/

## Key facts

- Cited by 370 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2017.

## Built on by (most cited first, 30 of 370)

- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [Effective Data Augmentation With Diffusion Models](https://mlsanity.com/paper/2302.07944/) (2023)
- [Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection](https://mlsanity.com/paper/2203.12208/) (2022)
- [SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption](https://mlsanity.com/paper/2106.15147/) (2021)
- [Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning](https://mlsanity.com/paper/2308.06038/) (2023)
- [A Comprehensive Survey of Dataset Distillation](https://mlsanity.com/paper/2301.05603/) (2023)
- [Inducing Causal Structure for Interpretable Neural Networks](https://mlsanity.com/paper/2112.00826/) (2021)
- [Contrastive Learning with Stronger Augmentations](https://mlsanity.com/paper/2104.07713/) (2021)
- [Image Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2204.08610/) (2022)
- [EnvEdit: Environment Editing for Vision-and-Language Navigation](https://mlsanity.com/paper/2203.15685/) (2022)
- [VeLO: Training Versatile Learned Optimizers by Scaling Up](https://mlsanity.com/paper/2211.09760/) (2022)
- [GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation](https://mlsanity.com/paper/2306.04607/) (2023)
- [Neural Data Augmentation via Example Extrapolation](https://mlsanity.com/paper/2102.01335/) (2021)
- [Hybrid Relation Guided Set Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2204.13423/) (2022)
- [Vision-Based Manipulators Need to Also See from Their Hands](https://mlsanity.com/paper/2203.12677/) (2022)
- [Large Scale Transfer Learning for Differentially Private Image Classification](https://mlsanity.com/paper/2205.02973/) (2022)
- [Tractable Regularization of Probabilistic Circuits](https://mlsanity.com/paper/2106.02264/) (2021)
- [Effective Evaluation of Deep Active Learning on Image Classification Tasks](https://mlsanity.com/paper/2106.15324/) (2021)
- [Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction](https://mlsanity.com/paper/2102.10106/) (2021)
- [Long-Tailed Class Incremental Learning](https://mlsanity.com/paper/2210.00266/) (2022)
- [Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification](https://mlsanity.com/paper/2111.06399/) (2021)
- [Self-supervised Monocular Depth Estimation: Let's Talk About The Weather](https://mlsanity.com/paper/2307.08357/) (2023)
- [Learning Universal Predictors](https://mlsanity.com/paper/2401.14953/) (2024)
- [Performance of a Geometric Deep Learning Pipeline for HL-LHC Particle Tracking](https://mlsanity.com/paper/2103.06995/) (2021)
- [CLCC: Contrastive Learning for Color Constancy](https://mlsanity.com/paper/2106.04989/) (2021)
- [Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View](https://mlsanity.com/paper/2401.11237/) (2024)
- [Dense Unsupervised Learning for Video Segmentation](https://mlsanity.com/paper/2111.06265/) (2021)
- [GaNDLF: A Generally Nuanced Deep Learning Framework for Scalable End-to-End Clinical Workflows in Medical Imaging](https://mlsanity.com/paper/2103.01006/) (2021)
- [A Deep Variational Approach to Clustering Survival Data](https://mlsanity.com/paper/2106.05763/) (2021)

## Abstract (arXiv)

In this paper, we explore and compare multiple solutions to the problem of data augmentation in image classification. Previous work has demonstrated the effectiveness of data augmentation through simple techniques, such as cropping, rotating, and flipping input images. We artificially constrain our access to data to a small subset of the ImageNet dataset, and compare each data augmentation technique in turn. One of the more successful data augmentations strategies is the traditional transformations mentioned above. We also experiment with GANs to generate images of different styles. Finally, we propose a method to allow a neural net to learn augmentations that best improve the classifier, which we call neural augmentation. We discuss the successes and shortcomings of this method on various datasets.