An overview of mixing augmentation methods and augmentation strategies

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 training data, required to prevent over-fitting, which domains entails significant cost manual data labeling. An alternative approach is application augmentation (DA) techniques that aim at model regularization by creating additional observations from available ones. survey focuses two DA research streams: image mixing and automated selection strategies. First, presented methods are briefly described, then qualitatively compared with respect their key characteristics. Various quantitative comparisons also included based results reported recent literature. review mainly covers published materials top-tier conferences leading journals years 2017-2021.