Robin Chan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Robin Chan has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Fabian Hüger
Volkswagen AG
1 shared publication - Hanno Gottschalk
School of Mathematics and Natural Sciences University of Wuppertal Germany
1 shared publication - Kira Maag
Volkswagen Group Innovation Volkswagen Group Innovation University of Wuppertal & ICMD University of Wuppertal & ICMD University of Wuppertal & ICMD University of Wuppertal & ICMD
1 shared publication - Matthias Rottmann
Institute of Computer Science Osnabruck University Germany
1 shared publication - Peter Schlicht
Volkswagen Group Innovation Wolfsburg Germany
1 shared publication
Latest Publications
- Open Access
Detection of False Positive and False Negative Samples in Semantic Segmentation
In recent years, deep learning methods have outperformed other methods in image recognition. This has fostered imagination of potential application of deep learning technology including safety relevant applications like the interpretation of medical images or autonomous driving. The passage from assistance of a human decision maker to ever more automated systems however increases the need to properly handle the failure modes of deep learning modules. In this contribution, we review a set of techniques for the self-monitoring of machine-learning algorithms based on uncertainty quantification. In particular, we apply this to the task of semantic segmentation, where the machine learning algorithm decomposes an image according to semantic categories. We discuss false positive and false negative error modes at instance-level and review techniques for the detection of such errors that have been recently proposed by the authors. We also give an outlook on future research directions.
Open AccessDetection of False Positive and False Negative Samples in Semantic Segmentation
In recent years, deep learning methods have outperformed other methods in image recognition. This has fostered imagination of potential application of deep learning technology including safety relevant applications like the interpretation of medical images or autonomous driving. The passage from assistance of a human decision maker to ever more automated systems however increases the need to properly handle the failure modes of deep learning modules. In this contribution, we review a set of techniques for the self-monitoring of machine-learning algorithms based on uncertainty quantification. In particular, we apply this to the task of semantic segmentation, where the machine learning algorithm decomposes an image according to semantic categories. We discuss false positive and false negative error modes at instance-level and review techniques for the detection of such errors that have been recently proposed by the authors. We also give an outlook on future research directions.