A Comprehensive Survey of Image Augmentation Techniques for Deep Learning

By Mingle Xu, Sook Yoon, Alvaro Fuentes, Dong Sun Park. Pattern Recognition, 2022

642 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/11cfe791cde06121ce53c84fc09e7939722f8464

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Massih-Reza Amini
2. Loïc Pauletto
3. Emilie Devijver
4. Yury Maximov
5. Vasilii Feofanov

In Computer Vision and Pattern Recognition

1. Massih-Reza Amini
2. Loïc Pauletto
3. Emilie Devijver
4. Yury Maximov
5. Vasilii Feofanov

Citations in the corpus

• Self-Training: A Survey (2022, positive): “Common approaches in self-supervised learning include predicting the order of shuffled image patches or their orientation [91], reconstructing corrupted images [23], filling in missing words in a sentence [8], or predicting future frames in a video sequence [69].”