Runtime Monitoring for Out-of-Distribution Detection in Object Detection Neural Networks
This addresses safety concerns for real-world applications like autonomous vehicles by providing a practical monitoring solution, though it is incremental as it builds on existing classification methods.
The paper tackled the problem of detecting out-of-distribution inputs in object detection neural networks by extending a runtime-monitoring approach from classification to perception systems, achieving documented efficacy in experimental OOD settings.
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.