Explaining YOLO: Leveraging Grad-CAM to Explain Object Detections

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.

Interpretability ML methods Security & robustness cs.CV cs.AI Explainable Artificial Intelligence (XAI)Adversarial Robustness in Machine Learning Advanced Neural Network Applications Computer Science

Paper

Similar papers

Computer Vision Explainability for Object Detection in Safety SurveillanceKumar Selvakumaran, Aman Sami, K. Anand et al.2023 · Lecture notes in networks and systems In Library

Explainable and Multi-Modal Cross-Context Object Localization Using YOLOv5, K-Means Color Analysis, and Regional HeatmapsMost. Mazriha Akter Mohua, Md.Nazmus Sakib2026 In Library

Pedestrian Detection: An Explainable ApproachHongbo Pang, Changcheng Huang2024 · International Conference on Machine Learning and Applications · 1 citation In Library

Image-Based Threat Detection and Explainability Investigation Using Incremental Learning and Grad-CAM with YOLOv8Zeynel Kutlu, Bülent Gürsel Emiroğlu2025 · Computers In Library

Optimisation of Deep Learning Small-Object Detectors with Novel Explainable VerificationElhassan Mohamed, Konstantinos Sirlantzis, Gareth Howells et al.2022 · Sensors · 8 citations In Library

Explainable AI: Objection Detection in Automated Vehicles using YOLOOsama Dad, Abdul Ahad Siddiqi2025 · International Journal of Computers and Informatics In Library

Comparison between Grad-CAM and EigenCAM on YOLOv5 detection modelArief Nur Rahman, Dian Andriana, Carmadi Machbub2022 In Library

Heatmap-based Explanation of YOLOv5 Object Detection with Layer-wise Relevance PropagationApostolos Karasmanoglou, Marios Antonakakis, Michalis Zervakis2022 · International Symposium on Telecommunications · 11 citations In Library

Enhancing Object Detection Interpretability for Class-Discriminative Visualizations with Grad-CAMMd Fatin Ishrak, Jannatun Nahar, Fairooz Afnad Faiza et al.2024 In Library

Towards Real-Time Explainable AI: Using Class Activation Mapping for Brake Prediction in YOLO-Based SystemsAmil Roohani Dar, Faisal Riaz2026 · BRAIN BROAD RESEARCH IN ARTIFICIAL INTELLIGENCE AND NEUROSCIENCE In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal