Strategy to Increase the Safety of a DNN-based Perception for HAD Systems
arXiv:2002.08935
Abstract
Safety is one of the most important development goals for highly automated driving (HAD) systems. This applies in particular to the perception function driven by Deep Neural Networks (DNNs). For these, large parts of the traditional safety processes and requirements are not fully applicable or sufficient. The aim of this paper is to present a framework for the description and mitigation of DNN insufficiencies and the derivation of relevant safety mechanisms to increase the safety of DNNs. To assess the effectiveness of these safety mechanisms, we present a categorization scheme for evaluation metrics.
References in corpus (7)
- Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
- Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
- AutoAugment: Learning Augmentation Policies from Data
- Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
- When Will AI Exceed Human Performance? Evidence from AI Experts
- A Unified View of Piecewise Linear Neural Network Verification
- Self-ensembling for visual domain adaptation