Paper ID: 2212.07773
Runtime Monitoring for Out-of-Distribution Detection in Object Detection Neural Networks
Vahid Hashemi, Jan Křetínsky, Sabine Rieder, Jessica Schmidt
Runtime monitoring provides a more realistic and applicable alternative to verification in the setting of real neural networks used in industry. It is particularly useful for detecting out-of-distribution (OOD) inputs, for which the network was not trained and can yield erroneous results. We extend a runtime-monitoring approach previously proposed for classification networks to perception systems capable of identification and localization of multiple objects. Furthermore, we analyze its adequacy experimentally on different kinds of OOD settings, documenting the overall efficacy of our approach.
Submitted: Dec 15, 2022