Please use this identifier to cite or link to this item:
Title: HayCAM: A Novel Visual Explanation for Deep Convolutional Neural Networks
Authors: Örnek, Ahmet H.
Ceylan, Murat
Keywords: classification
class activation mapping
explainable artificial intelligence
visual explanation
weakly-supervised object detection
Issue Date: 2022
Publisher: Int Information & Engineering Technology Assoc
Abstract: Explaining the decision mechanism of Deep Convolutional Neural Networks (CNNs) is a new and challenging area because of the Black Box nature of CNN's. Class Activation Mapping (CAM) as a visual explainable method is used to highlight important regions of input images by using classification gradients. The lack of the current methods is to use all of the filters in the last convolutional layer which causes scattered and unfocused activation mapping. HayCAMas a novel visualization method provides better activation mapping and therefore better localization by using dimension reduction. It has been shown with mask detection use case that input images are fed into the CNN model and bounding boxes are drawn over the generated activation maps (i.e. weakly-supervised object detection) by three different CAM methods. IoU values are obtained as 0.1922 for GradCAM, 0.2472 for GradCAM++, 0.3386 for EigenCAM, and 0.3487 for the proposed HayCAM. The results show that HayCAM achieves the best activation mapping with dimension reduction.
ISSN: 0765-0019
Appears in Collections:Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collections
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collections

Files in This Item:
File SizeFormat 
39.05_29.pdf1.48 MBAdobe PDFView/Open
Show full item record

CORE Recommender

Page view(s)

checked on Sep 18, 2023


checked on Sep 18, 2023

Google ScholarTM



Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.