A Comprehensive Survey of Image Augmentation Techniques for Deep Learning

TL;DR

This survey comprehensively reviews image augmentation techniques for deep learning, categorizing methods into model-free, model-based, and policy-based approaches, and discusses current trends and applications in the field.

Contribution

It introduces a novel informative taxonomy for image augmentation algorithms and provides insights into their applications and future directions.

Findings

Categorizes augmentation methods into three main types.

Highlights the importance of understanding augmentation for practical applications.

Discusses emerging trends like unsupervised learning and theoretical analysis.

Abstract

Deep learning has been achieving decent performance in computer vision requiring a large volume of images, however, collecting images is expensive and difficult in many scenarios. To alleviate this issue, many image augmentation algorithms have been proposed as effective and efficient strategies. Understanding current algorithms is essential to find suitable methods or develop novel techniques for given tasks. In this paper, we perform a comprehensive survey on image augmentation for deep learning with a novel informative taxonomy. To get the basic idea why we need image augmentation, we introduce the challenges in computer vision tasks and vicinity distribution. Then, the algorithms are split into three categories; model-free, model-based, and optimizing policy-based. The model-free category employs image processing methods while the model-based method leverages trainable image generation models. In contrast, the optimizing policy-based approach aims to find the optimal operations or their combinations. Furthermore, we discuss the current trend of common applications with two more active topics, leveraging different ways to understand image augmentation, such as group and kernel theory, and deploying image augmentation for unsupervised learning. Based on the analysis, we believe that our survey gives a better understanding helpful to choose suitable methods or design novel algorithms for practical applications.