paper-with-me

홈 › Papers

Explaining YOLO: Leveraging Grad-CAM to Explain Object Detections

2022-11-22 · Armin Kirchknopf, Djordje Slijepcevic, Ilkay Wunderlich, Michael Breiter, Johannes Traxler, Matthias Zeppelzauer

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.

📄 PDF Abstract BibTeX arXiv:2211.12108

Code (0)

등록된 구현이 없습니다.

Tasks

Object

Similar Papers 제목 키워드 기반

You Only Explain Once

2023-11-23 · David A. Kelly, Hana Chockler, Daniel Kroening, Nathan Blake 외

In this paper, we propose a new black-box explainability algorithm and tool, YO-ReX, for efficient explanation of the outputs of object detectors. The new algorithm computes explanations for all objects detected in the i…

YOLO -- You only look 10647 times

2022-01-16 · Christian Limberg, Andrew Melnik, Augustin Harter, Helge Ritter

With this work we are explaining the "You Only Look Once" (YOLO) single-stage object detection approach as a parallel classification of 10647 fixed region proposals. We support this view by showing that each of YOLOs out…

Classificationimage-classificationImage ClassificationObject+3

An Empirical Study on the Robustness of YOLO Models for Underwater Object Detection

2025-09-22 · Edwine Nabahirwa, Wei Song, Minghua Zhang, Shufan Chen arxiv

Underwater object detection (UOD) remains a critical challenge in computer vision due to underwater distortions which degrade low-level features and compromise the reliability of even state-of-the-art detectors. While YO…

Real-Time Object DetectionDomain Adaptation

Align-Deform-Subtract: An Interventional Framework for Explaining Object Differences

2022-03-09 · Cian Eastwood, Li Nanbo, Christopher K. I. Williams

Given two object images, how can we explain their differences in terms of the underlying object properties? To address this question, we propose Align-Deform-Subtract (ADS) -- an interventional framework for explaining o…

counterfactualObject

Towards Better Explanations for Object Detection

2023-06-05 · Van Binh Truong, Truong Thanh Hung Nguyen, Vo Thanh Khang Nguyen, Quoc Khanh Nguyen 외

Recent advances in Artificial Intelligence (AI) technology have promoted their use in almost every field. The growing complexity of deep neural networks (DNNs) makes it increasingly difficult and important to explain the…

Objectobject-detectionObject Detection