DeepAI AI Chat
Log In Sign Up

Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Driving

by   Victor Besnier, et al.

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.


page 1

page 4


Safety Metrics for Semantic Segmentation in Autonomous Driving

Within the context of autonomous driving, safety-related metrics for dee...

Robust Deep Learning for Autonomous Driving

The last decade's research in artificial intelligence had a significant ...

The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation

Deep learning has enabled impressive progress in the accuracy of semanti...

Towards Defensive Autonomous Driving: Collecting and Probing Driving Demonstrations of Mixed Qualities

Designing or learning an autonomous driving policy is undoubtedly a chal...

Injecting Planning-Awareness into Prediction and Detection Evaluation

Detecting other agents and forecasting their behavior is an integral par...

Behavioral event detection and rate estimation for autonomous vehicle evaluation

Autonomous vehicles are continually increasing their presence on public ...

Multi-Loss Sub-Ensembles for Accurate Classification with Uncertainty Estimation

Deep neural networks (DNNs) have made a revolution in numerous fields du...