A Comprehensive Survey of Image Augmentation Techniques for Deep Learning

TLDR

Deep learning in computer vision requires large image datasets, but collecting them is costly and challenging, so many augmentation algorithms have been proposed to alleviate this issue and understanding them is essential for selecting suitable methods and developing new ones. The study conducts a comprehensive survey of image augmentation for deep learning, introducing a novel taxonomy and outlining challenges in computer vision tasks. The survey classifies augmentation algorithms into model‑free, model‑based, and policy‑based categories, describing image‑processing methods, generative‑model synthesis, and optimization of operation combinations, respectively. The survey enhances understanding for selecting suitable augmentation methods and designing novel algorithms.

Abstract

Although deep learning has achieved satisfactory performance in computer vision, a large volume of images is required. However, collecting images is often expensive and challenging. Many image augmentation algorithms have been proposed to alleviate this issue. Understanding existing algorithms is, therefore, essential for finding suitable and developing novel methods for a given task. In this study, we perform a comprehensive survey of image augmentation for deep learning using a novel informative taxonomy. To examine the basic objective of image augmentation, we introduce challenges in computer vision tasks and vicinity distribution. The algorithms are then classified among three categories: model-free, model-based, and optimizing policy-based. The model-free category employs the methods from image processing, whereas the model-based approach leverages image generation models to synthesize images. In contrast, the optimizing policy-based approach aims to find an optimal combination of operations. Based on this analysis, we believe that our survey enhances the understanding necessary for choosing suitable methods and designing novel algorithms.