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

arXiv: https://arxiv.org/abs/2211.12108 · HTML: https://mlsanity.com/paper/2211.12108/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 9 references that are in the map.
- First posted on arXiv 22 Nov 2022.

## Builds on (most cited first, 6 of 6)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Deep Learning for Generic Object Detection: A Survey](https://mlsanity.com/paper/1809.02165/) (2018)
- [Learning to Explain: An Information-Theoretic Perspective on Model Interpretation](https://mlsanity.com/paper/1802.07814/) (2018)
- [Black-box Explanation of Object Detectors via Saliency Maps](https://mlsanity.com/paper/2006.03204/) (2020)

## Built on by (most cited first, 6 of 6)

- [Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainability](https://mlsanity.com/paper/2304.14864/) (2023)
- [Deep Unfolding Multi-modal Image Fusion Network via Attribution Analysis](https://mlsanity.com/paper/2502.01467/) (2025)
- [You Only Explain Once](https://mlsanity.com/paper/2311.14081/) (2023)
- [On the Black-box Explainability of Object Detection Models for Safe and Trustworthy Industrial Applications](https://mlsanity.com/paper/2411.00818/) (2024)
- [ProtoP-OD: Explainable Object Detection with Prototypical Parts](https://mlsanity.com/paper/2402.19142/) (2024)
- [Reconstructed holograms and explanation-aware evaluation for low-cost computational pollen analysis in veterinary cytology](https://mlsanity.com/paper/2609.23017/) (2026)

## Abstract (arXiv)

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.