PUB - Publikationen an der Universität Bielefeld

Semantic segmentation is a crucial component for perception in automated driving. Deep neural networks (DNNs) are commonly used for this task, and they are usually trained on a closed set of object classes appearing in a closed operational domain. However, this is in contrast to the open world assumption in automated driving that DNNs are deployed to. Therefore, DNNs necessarily face data that they have never encountered previously, also known asanomalies, which are extremely safety-critical to properly cope with. In this chapter, we first give an overview about anomalies from an information-theoretic perspective. Next, we review research in detecting unknown objects in semantic segmentation. We present a method outperforming recent approaches by training for high entropy responses on anomalous objects, which is in line with our theoretical findings. Finally, we propose a method to assess the occurrence frequency of anomalies in order to select anomaly types to include into a model’s set of semantic categories. We demonstrate that those anomalies can then be learned in an unsupervised fashion which is particularly suitable in online applications.