# Explaining YOLO: Leveraging Grad-CAM to Explain Object Detections

Source: [Explaining YOLO: Leveraging Grad-CAM to Explain Object Detections](<https://www.sota2.com/research/paper/68fa6dfc1e209131cea3d2f4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:47:11.173Z

Authors: Armin Kirchknopf, Djordje Slijepcevic, Ilkay Wunderlich, Michael Breiter, Johannes Traxler, Matthias Zeppelzauer

Published: 2022-11-22T09:19:13.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2211.12108>)

[PDF](<https://arxiv.org/pdf/2211.12108.pdf>)
