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