Explainable Object Detection for Uncrewed Aerial Vehicles using KernelSHAP
Maxwell Hogan, Nabil Aouf, Phillippa Spencer, Jay Almond
Abstract
While the field of object detection has seen remarkable performance gains since the incorporation of Deep Neural Networks (DNNs), a significant drawback in DNN detection algorithms is that they lack transparency, making their behaviour somewhat unpredictable. Without transparency, employing DNNs for on-board object detection on Uncrewed Aerial Vehicles (UAVs) could have massive societal and safety consequences. In this paper, we propose adopting a proven explainer, KernelSHAP, to provide visual explanations for bounding boxes produced by detection algorithms intended for on-board UAVs. Our explainer can identify the important parts of an image that assisted a given detection or contributed to a specific failure mode. We evaluate our explainer’s discriminative ability on aerial imagery through a pointing metric and an automatic deletion/insertion metric. We further assess our explainer by intentionally introducing a bias to the dataset for it to detect and using that bias to simulate failure modes that can then be discovered using our explainer.