Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.13091/5407
Title: HayCAMJ: A new method to uncover the importance of main filter for small objects in explainable artificial intelligence
Authors: Ornek, A.H.
Ceylan, M.
Keywords: Class activation mapping
Deep learning
Explainable artificial intelligence
Visual explanation
Weakly supervised object detection
Chemical activation
Deep learning
Object recognition
Activation mapping
Class activation mapping
Deep learning
Explainable artificial intelligence
Importance map
Input image
Objects detection
Small objects
Visual explanation
Weakly supervised object detection
Object detection
Publisher: Springer Science and Business Media Deutschland GmbH
Abstract: Visual XAI methods enable experts to reveal importance maps highlighting intended classes over input images. This research paper presents a novel approach to visual explainable artificial intelligence (XAI) for object detection in deep learning models. The study investigates the effectiveness of activation maps generated by five different methods, namely GradCAM, GradCAM++, EigenCAM, HayCAM, and a newly proposed method called "HayCAMJ", in detecting objects within images. The experiments were conducted on two datasets (Pascal VOC 2007 and Pascal VOC 2012) and three models (ResNet18, ResNet34, and MobileNet). Zero padding was applied to resize and center the objects due to the large objects in the images. The results show that HayCAMJ performs better than other XAI techniques in detecting small objects. This finding suggests that HayCAMJ has the potential to become a promising new approach for object detection in deep classification models. © The Author(s) 2024.
URI: https://doi.org/10.1007/s00521-024-09640-y
https://hdl.handle.net/20.500.13091/5407
ISSN: 0941-0643
Appears in Collections:Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collections

Show full item record



CORE Recommender

Page view(s)

34
checked on Jul 15, 2024

Google ScholarTM

Check




Altmetric


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