文章基本信息

标题：Survey on Videos Data Augmentation for Deep Learning Models
本地全文：下载
作者：Nino Cauli ; Diego Reforgiato Recupero
期刊名称：Future Internet
电子版ISSN：1999-5903
出版年度：2022
卷号：14
期号：3
页码：93
DOI：10.3390/fi14030093
语种：English
出版社：MDPI Publishing
摘要：In most Computer Vision applications, Deep Learning models achieve state-of-the-art performances. One drawback of Deep Learning is the large amount of data needed to train the models. Unfortunately, in many applications, data are difficult or expensive to collect. Data augmentation can alleviate the problem, generating new data from a smaller initial dataset. Geometric and color space image augmentation methods can increase accuracy of Deep Learning models but are often not enough. More advanced solutions are Domain Randomization methods or the use of simulation to artificially generate the missing data. Data augmentation algorithms are usually specifically designed for single images. Most recently, Deep Learning models have been applied to the analysis of video sequences. The aim of this paper is to perform an exhaustive study of the novel techniques of video data augmentation for Deep Learning models and to point out the future directions of the research on this topic.