Image Data Augmentation for Deep Learning: A Survey

TL;DR

This survey addresses the challenge of limited labeled image data by presenting a comprehensive taxonomy of image data augmentation methods, ranging from basic transformations and erasing/mixing strategies to advanced policy search, feature-space augmentation, and GAN-based synthesis. It provides systematic, task-aware evaluations across semantic segmentation, image classification, and object detection to quantify gains and reveal model-dependent effects. The work highlights the need for theoretical grounding, standardized evaluation metrics for synthetic data, and careful selection and combination of augmentation techniques per task. Overall, it offers practical guidance and identifies key open challenges to steer future research in image data augmentation.

Abstract

Deep learning has achieved remarkable results in many computer vision tasks. Deep neural networks typically rely on large amounts of training data to avoid overfitting. However, labeled data for real-world applications may be limited. By improving the quantity and diversity of training data, data augmentation has become an inevitable part of deep learning model training with image data. As an effective way to improve the sufficiency and diversity of training data, data augmentation has become a necessary part of successful application of deep learning models on image data. In this paper, we systematically review different image data augmentation methods. We propose a taxonomy of reviewed methods and present the strengths and limitations of these methods. We also conduct extensive experiments with various data augmentation methods on three typical computer vision tasks, including semantic segmentation, image classification and object detection. Finally, we discuss current challenges faced by data augmentation and future research directions to put forward some useful research guidance.

Figures (1)

• Figure 1: A taxonomy of image data augmentation methods.