# Improving Deep Learning using Generic Data Augmentation

arXiv: https://arxiv.org/abs/1708.06020 · HTML: https://mlsanity.com/paper/1708.06020/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Aug 2017.

## Built on by (most cited first, 30 of 36)

- [An Empirical Survey of Data Augmentation for Limited Data Learning in NLP](https://mlsanity.com/paper/2106.07499/) (2021)
- [How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization](https://mlsanity.com/paper/2210.06441/) (2022)
- [BSUV-Net 2.0: Spatio-Temporal Data Augmentations for Video-Agnostic Supervised Background Subtraction](https://mlsanity.com/paper/2101.09585/) (2021)
- [Improved YOLOv5 network for real-time multi-scale traffic sign detection](https://mlsanity.com/paper/2112.08782/) (2021)
- [Practice Makes a Solver Perfect: Data Augmentation for Math Word Problem Solvers](https://mlsanity.com/paper/2205.00177/) (2022)
- [RITUAL: Random Image Transformations as a Universal Anti-hallucination Lever in Large Vision Language Models](https://mlsanity.com/paper/2405.17821/) (2024)
- [Sill-Net: Feature Augmentation with Separated Illumination Representation](https://mlsanity.com/paper/2102.03539/) (2021)
- [Invariance encoding in sliced-Wasserstein space for image classification with limited training data](https://mlsanity.com/paper/2201.02980/) (2022)
- [DiffML: End-to-end Differentiable ML Pipelines](https://mlsanity.com/paper/2207.01269/) (2022)
- [Apple Counting using Convolutional Neural Networks](https://mlsanity.com/paper/2208.11566/) (2022)
- [Image Captioning using Deep Stacked LSTMs, Contextual Word Embeddings and Data Augmentation](https://mlsanity.com/paper/2102.11237/) (2021)
- [Principled Ultrasound Data Augmentation for Classification of Standard Planes](https://mlsanity.com/paper/2103.07895/) (2021)
- [Fast Jacobian-Vector Product for Deep Networks](https://mlsanity.com/paper/2104.00219/) (2021)
- [Landmarks Augmentation with Manifold-Barycentric Oversampling](https://mlsanity.com/paper/2104.00925/) (2021)
- [Controllable Data Augmentation Through Deep Relighting](https://mlsanity.com/paper/2110.13996/) (2021)
- [PIAT: Physics Informed Adversarial Training for Solving Partial Differential Equations](https://mlsanity.com/paper/2207.06647/) (2022)
- [Agile Effort Estimation: Have We Solved the Problem Yet? Insights From A Replication Study](https://mlsanity.com/paper/2201.05401/) (2022)
- [Feature transforms for image data augmentation](https://mlsanity.com/paper/2201.09700/) (2022)
- [Image Augmentation for Satellite Images](https://mlsanity.com/paper/2207.14580/) (2022)
- [An Improved Data Augmentation Scheme for Model Predictive Control Policy Approximation](https://mlsanity.com/paper/2303.05607/) (2023)
- [How Important are Data Augmentations to Close the Domain Gap for Object Detection in Orbit?](https://mlsanity.com/paper/2410.15766/) (2024)
- [Transformer-based Map Matching Model with Limited Ground-Truth Data using Transfer-Learning Approach](https://mlsanity.com/paper/2108.00439/) (2021)
- [Iterative training of robust k-space interpolation networks for improved image reconstruction with limited scan specific training samples](https://mlsanity.com/paper/2201.03560/) (2022)
- [Video2IMU: Realistic IMU features and signals from videos](https://mlsanity.com/paper/2202.06547/) (2022)
- [Application of multilayer perceptron with data augmentation in nuclear physics](https://mlsanity.com/paper/2205.07953/) (2022)
- [The Lean Data Scientist: Recent Advances towards Overcoming the Data Bottleneck](https://mlsanity.com/paper/2211.07959/) (2022)
- [Embarrassingly Simple MixUp for Time-series](https://mlsanity.com/paper/2304.04271/) (2023)
- [Object Detection for Understanding Assembly Instruction Using Context-aware Data Augmentation and Cascade Mask R-CNN](https://mlsanity.com/paper/2101.02509/) (2021)
- [Explainability Guided Multi-Site COVID-19 CT Classification](https://mlsanity.com/paper/2103.13677/) (2021)
- [Deep learning facilitates fully automated brain image registration of optoacoustic tomography and magnetic resonance imaging](https://mlsanity.com/paper/2109.01880/) (2021)

## Abstract (arXiv)

Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating the training set with label preserving transformations. Recently there has been extensive use of generic data augmentation to improve Convolutional Neural Network (CNN) task performance. This study benchmarks various popular data augmentation schemes to allow researchers to make informed decisions as to which training methods are most appropriate for their data sets. Various geometric and photometric schemes are evaluated on a coarse-grained data set using a relatively simple CNN. Experimental results, run using 4-fold cross-validation and reported in terms of Top-1 and Top-5 accuracy, indicate that cropping in geometric augmentation significantly increases CNN task performance.