Explaining YOLO: Leveraging Grad-CAM to Explain Object Detections

Armin Kirchknopf; Djordje Slijepcevic; Ilkay Wunderlich; Michael Breiter; Johannes Traxler; Matthias Zeppelzauer

doi:10.3217/978-3-85125-869-1-13

paper

Explaining YOLO: Leveraging Grad-CAM to Explain Object Detections

arXiv:2211.12108 · doi:10.3217/978-3-85125-869-1-13

Abstract

We investigate the problem of explainability for visual object detectors. Specifically, we demonstrate on the example of the YOLO object detector how to integrate Grad-CAM into the model architecture and analyze the results. We show how to compute attribution-based explanations for individual detections and find that the normalization of the results has a great impact on their interpretation.