Volltext-Downloads (blau) und Frontdoor-Views (grau)

Investigating Semantic Augmentation in Virtual Environments for Image Segmentation Using Convolutional Neural Networks

  • Collecting real-world data for the training of neural networks is enormously time-consuming and expensive. As such, the concept of virtualizing the domain and creating synthetic data has been analyzed in many instances. This virtualization offers many possibilities of changing the domain, and with that, enabling the relatively fast creation of data. It also offers the chance to enhance necessary augmentations with additional semantic information when compared with conventional augmentation methods. This raises the question of whether such semantic changes, which can be seen as augmentations of the virtual domain, contribute to better results for neural networks, when trained with data augmented this way. In this paper, a virtual dataset is presented, including semantic augmentations and automatically generated annotations, as well as a comparison between semantic and conventional augmentation for image data. It is determined that the results differ only marginally for neural network models trained with the two augmentation approaches.
Author:Joshua Ganter, Simon Löffler, Ron Metzger, Katharina Ußling, Christoph MüllerORCiDGND
Parent Title (English):Journal of Imaging
Document Type:Article (peer-reviewed)
Year of Completion:2021
Release Date:2021/12/10
Tag:Convolutional neural networks; Image segmentation; Semantic augmentation; Virtual image data
First Page:146
Last Page:162
Open-Access-Status: Open Access 
Licence (German):License LogoCreative Commons - CC BY - Namensnennung 4.0 International