Research Trends and Applications of Data Augmentation Algorithms

TL;DR

This paper analyzes the evolution, applications, and research gaps of data augmentation algorithms in machine learning, highlighting their importance in improving model performance with limited data and computational resources.

Contribution

It provides a comprehensive review of data augmentation techniques, research trends, and identifies gaps and future directions in the field.

Findings

Data augmentation enhances model performance in limited data scenarios.

Research trends show increasing focus on transferability and application-specific methods.

Identifies gaps in current data augmentation approaches and suggests future research directions.

Abstract

In the Machine Learning research community, there is a consensus regarding the relationship between model complexity and the required amount of data and computation power. In real world applications, these computational requirements are not always available, motivating research on regularization methods. In addition, current and past research have shown that simpler classification algorithms can reach state-of-the-art performance on computer vision tasks given a robust method to artificially augment the training dataset. Because of this, data augmentation techniques became a popular research topic in recent years. However, existing data augmentation methods are generally less transferable than other regularization methods. In this paper we identify the main areas of application of data augmentation algorithms, the types of algorithms used, significant research trends, their progression over time and research gaps in data augmentation literature. To do this, the related literature was collected through the Scopus database. Its analysis was done following network science, text mining and exploratory analysis approaches. We expect readers to understand the potential of data augmentation, as well as identify future research directions and open questions within data augmentation research.