Plants Don't Walk on the Street: Common-Sense Reasoning for Reliable Semantic Segmentation

no code implementations • 19 Apr 2021 • Linara Adilova, Elena Schulz, Maram Akila, Sebastian Houben, Jan David Schneider, Fabian Hueger, Tim Wirtz

Data-driven sensor interpretation in autonomous driving can lead to highly implausible predictions as can most of the time be verified with common-sense knowledge.

Autonomous Driving Common Sense Reasoning +2

Street-Map Based Validation of Semantic Segmentation in Autonomous Driving

no code implementations • 15 Apr 2021 • Laura von Rueden, Tim Wirtz, Fabian Hueger, Jan David Schneider, Nico Piatkowski, Christian Bauckhage

Lastly, we present quantitative results on the Cityscapes dataset indicating that our validation approach can indeed uncover errors in semantic segmentation masks.

Autonomous Driving Position +2

Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimates

1 code implementation • 14 Dec 2020 • Kira Maag, Matthias Rottmann, Serin Varghese, Fabian Hueger, Peter Schlicht, Hanno Gottschalk

In this paper, we present a time-dynamic approach to model uncertainties of instance segmentation networks and apply this to the detection of false positives as well as the estimation of prediction quality.

Instance Segmentation object-detection +4

Towards Map-Based Validation of Semantic Segmentation Masks

no code implementations • 3 Nov 2020 • Laura von Rueden, Tim Wirtz, Fabian Hueger, Jan David Schneider, Christian Bauckhage

Artificial intelligence for autonomous driving must meet strict requirements on safety and robustness.

Autonomous Driving BIG-bench Machine Learning +1

Towards More Realistic Neural Network Uncertainties

no code implementations • 25 Sep 2019 • Joachim Sicking, Alexander Kister, Matthias Fahrland, Stefan Eickeler, Fabian Hueger, Stefan Rueping, Peter Schlicht, Tim Wirtz

Statistical models are inherently uncertain.