Image Data Augmentation for Deep Learning: A Survey

TL;DR

This survey comprehensively reviews image data augmentation techniques for deep learning, categorizing methods, analyzing their strengths and limitations, and evaluating their impact on various computer vision tasks.

Contribution

It provides a systematic taxonomy of image data augmentation methods, along with experimental comparisons and insights into future research directions.

Findings

Different augmentation methods improve model performance variably.

Augmentation techniques have distinct strengths and limitations.

Future research should address current challenges in 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.