Explaining YOLO: Leveraging Grad-CAM to Explain Object Detections

11/22/2022

∙

by   Armin Kirchknopf, et al.

∙

0

∙

share

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.