Back to Search Start Over

Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Driving

Authors :
David Picard
Alexandre Briot
Victor Besnier
VALEO
Source :
2021 IEEE International Conference on Image Processing (ICIP), 2021 IEEE International Conference on Image Processing (ICIP), Sep 2021, Anchorage, United States. pp.3353-3357, ⟨10.1109/ICIP42928.2021.9506719⟩
Publication Year :
2021

Abstract

In this paper, we show how uncertainty estimation can be leveraged to enable safety critical image segmentation in autonomous driving, by triggering a fallback behavior if a target accuracy cannot be guaranteed. We introduce a new uncertainty measure based on disagreeing predictions as measured by a dissimilarity function. We propose to estimate this dissimilarity by training a deep neural architecture in parallel to the task-specific network. It allows this observer to be dedicated to the uncertainty estimation, and let the task-specific network make predictions. We propose to use self-supervision to train the observer, which implies that our method does not require additional training data. We show experimentally that our proposed approach is much less computationally intensive at inference time than competing methods (e.g. MCDropout), while delivering better results on safety-oriented evaluation metrics on the CamVid dataset, especially in the case of glare artifacts.

Details

Language :
English
Database :
OpenAIRE
Journal :
2021 IEEE International Conference on Image Processing (ICIP), 2021 IEEE International Conference on Image Processing (ICIP), Sep 2021, Anchorage, United States. pp.3353-3357, ⟨10.1109/ICIP42928.2021.9506719⟩
Accession number :
edsair.doi.dedup.....77e24753ac7d646086487d094ed5d7b2
Full Text :
https://doi.org/10.1109/ICIP42928.2021.9506719⟩