# A Preliminary Study on Data Augmentation of Deep Learning for Image Classification

arXiv: https://arxiv.org/abs/1906.11887 · HTML: https://mlsanity.com/paper/1906.11887/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2019.

## Built on by (most cited first, 8 of 8)

- [Is Your HD Map Constructor Reliable under Sensor Corruptions?](https://mlsanity.com/paper/2406.12214/) (2024)
- [Data Scarcity in Recommendation Systems: A Survey](https://mlsanity.com/paper/2312.10073/) (2023)
- [Image Augmentation for Satellite Images](https://mlsanity.com/paper/2207.14580/) (2022)
- [Exploring Stronger Transformer Representation Learning for Occluded Person Re-Identification](https://mlsanity.com/paper/2410.15613/) (2024)
- [A Probabilistic Framework for Knowledge Graph Data Augmentation](https://mlsanity.com/paper/2110.13205/) (2021)
- [A Data Augmented Approach to Transfer Learning for Covid-19 Detection](https://mlsanity.com/paper/2108.02870/) (2021)
- [A Computer Vision-Based Quality Assessment Technique for the automatic control of consumables for analytical laboratories](https://mlsanity.com/paper/2404.10454/) (2024)
- [A Systematic Evaluation of the COTQ Provincial Land Cover Product: Structural Consistency, Spectral Separability, and Relative Positioning Against ESA, ESRI, and Google Products](https://mlsanity.com/paper/2609.17731/) (2026)

## Abstract (arXiv)

Deep learning models have a large number of freeparameters that need to be calculated by effective trainingof the models on a great deal of training data to improvetheir generalization performance. However, data obtaining andlabeling is expensive in practice. Data augmentation is one of themethods to alleviate this problem. In this paper, we conduct apreliminary study on how three variables (augmentation method,augmentation rate and size of basic dataset per label) can affectthe accuracy of deep learning for image classification. The studyprovides some guidelines: (1) it is better to use transformationsthat alter the geometry of the images rather than those justlighting and color. (2) 2-3 times augmentation rate is good enoughfor training. (3) the smaller amount of data, the more obviouscontributions could have.