Safety Metrics for Semantic Segmentation in Autonomous Driving

A causal model of safety assurance for machine learning

“…Previous work on the safety assurance of machine learning has focused on the structure of the assurance case and associated processes with respect to exist-ing safety standards [6,27,16,3,10]. Other work has focused on the effectiveness of specific metrics and measures on providing meaningful statements related to safety properties of the ML function [11,20,29,12]. To date, however, little work has appeared that places such detailed methods and metrics within an overall assurance argument context.…”