The conference Deep Learning Theory and Applications (DeLTA 2020), a sister conference of ICINCO, took place for the first time this year. Due to the Covid-19 pandemic, it was held entirely virtually instead of in Lieusant, Paris. The publication entitled "Data Augmentation for Semantic Segmentation in the context of Carbon Fiber Defect Detection using Adversarial Learning" was initiated in partnership between Fraunhofer IGCV and the Chair of Human-Centered Multimedia headed by Prof. Dr. Elisabeth André.

The presented method opens new possibilities for the development and configuration of image processing systems for continuous processes. Previous AI solutions require large amounts of training data, which can only be generated with great effort. The approach of Mertes, Margraf, Kommer, Geinitz and André enables a higher performance of artificial neural networks for semantic segmentation tasks by generating artificial data.?