Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Driving
arXiv:2105.13688
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.
References in corpus (10)
- Rethinking Atrous Convolution for Semantic Image Segmentation
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
- Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
- On Calibration of Modern Neural Networks
- Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding
- Bayesian Uncertainty Estimation for Batch Normalized Deep Networks
- The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation
- Evaluating Uncertainty Quantification in End-to-End Autonomous Driving Control
- Inhibited Softmax for Uncertainty Estimation in Neural Networks
- Dropout Distillation for Efficiently Estimating Model Confidence