Detection of False Positive and False Negative Samples in Semantic Segmentation

Matthias Rottmann1,a, Kira Maag1,b, Robin Chan1,c, Fabian Hüger2,e, Peter Schlicht2,f and Hanno Gottschalk1,d

1University of Wuppertal & ICMD
arottmann@math.uni-wuppertal.de
bmaag@math.uni-wuppertal.de
cchan@math.uni-wuppertal.de
dhanno.gottschalk@uni-wuppertal.de
2Volkswagen Group Innovation
efabian.hueger@volkswagen.de
fpeter.schlicht@volkswagen.de

ABSTRACT

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.

Keywords: Deep Learning, Semantic Segmentation, False Positive And False Negative Detection.



Full Text (PDF)