An overview of mixing augmentation methods and augmentation strategies

TL;DR

This paper surveys recent image mixing and automated augmentation strategy methods in deep learning, highlighting their characteristics, comparisons, and results to guide effective data augmentation in computer vision.

Contribution

It provides a comprehensive overview and qualitative and quantitative comparison of recent mixing and automated augmentation methods from top-tier publications.

Findings

Mixing augmentation methods improve model regularization.

Automated augmentation strategies optimize data transformations.

Recent methods show significant performance gains in vision tasks.

Abstract

Deep Convolutional Neural Networks have made an incredible progress in many Computer Vision tasks. This progress, however, often relies on the availability of large amounts of the training data, required to prevent over-fitting, which in many domains entails significant cost of manual data labeling. An alternative approach is application of data augmentation (DA) techniques that aim at model regularization by creating additional observations from the available ones. This survey focuses on two DA research streams: image mixing and automated selection of augmentation strategies. First, the presented methods are briefly described, and then qualitatively compared with respect to their key characteristics. Various quantitative comparisons are also included based on the results reported in recent DA literature. This review mainly covers the methods published in the materials of top-tier conferences and in leading journals in the years 2017-2021.