HIGHLIGHTS
- who: Recognition Use Case and colleagues from the RD ADAS Software Platform, Mercedes-Benz AG, Sindelfingen, Germany , Institute of Measurement Sensor Technology, Technical University of Kaiserslautern, Kaiserslautern, Germany have published the research: Insufficiency-Driven DNN Error Detection in the Context of SOTIF on Traffic Sign Recognition Use Case, in the Journal: (JOURNAL)
- what: The authors demonstrate that the approach is able to handle all these error types. The authors show the performance benefit of the method compared to a baseline DNN to state of the art DNN monitoring methods. To address these gaps, the authors . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.