Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.13091/5366
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Örnek, Ahmet Haydar | - |
dc.contributor.author | Ceylan, Murat | - |
dc.date.accessioned | 2024-04-20T13:05:03Z | - |
dc.date.available | 2024-04-20T13:05:03Z | - |
dc.date.issued | 2024 | - |
dc.identifier.issn | 0765-0019 | - |
dc.identifier.issn | 1958-5608 | - |
dc.identifier.uri | https://doi.org/10.18280/ts.410105 | - |
dc.identifier.uri | https://hdl.handle.net/20.500.13091/5366 | - |
dc.description.abstract | Deep learning models are proficient at predicting target classes, but they need to explain their predictions. Explainable Artificial Intelligence (XAI) offers a promising solution by providing both transparency and object detection capabilities to classification models. Mask detection plays a crucial role in ensuring the safety and well-being of individuals by preventing the spread of infectious diseases. A new visual XAI method called HayCAM+ is proposed to address the limitations of the previous method known as HayCAM, such as the need to select the number of filters as a hyper -parameter and the use of fully -connected layers. When object detection is performed using activation maps created via various methods, including GradCAM, EigenCAM, GradCAM++, LayerCAM, HayCAM, and HayCAM+, it is found that HayCAM+ provides the best results with an IoU score of 0.3740 (GradCAM: 0.1922, GradCAM++: 0.2472, EigenCAM: 0.3386, LayerCAM: 0.2476, HayCAM: 0.3487) and a Dice score of 0.5376 (GradCAM: 0.3153, GradCAM++: 0.3923, EigenCAM: 0.5003, LayerCAM: 0.3928, HayCAM: 0.5098). By using dynamical dimension reduction to eliminate unrelated filters in the last convolutional layer, HayCAM+ generates more focused activation maps. The results demonstrate that HayCAM+ is an advanced activation map method for explaining decisions and detecting objects using deep classification models. | en_US |
dc.description.sponsorship | Huawei Tuerkiye RD Center | en_US |
dc.description.sponsorship | This work was supported by Huawei Tuerkiye R&D Center. | en_US |
dc.language.iso | en | en_US |
dc.publisher | Int Information & Engineering Technology Assoc | en_US |
dc.relation.ispartof | Traitement Du Signal | en_US |
dc.rights | info:eu-repo/semantics/openAccess | en_US |
dc.subject | class activation mapping | en_US |
dc.subject | explainable artificial intelligence | en_US |
dc.subject | HayCAM | en_US |
dc.subject | deep learning | en_US |
dc.subject | visual explanation | en_US |
dc.subject | weakly-supervised object detection | en_US |
dc.subject | Artificial-Intelligence | en_US |
dc.subject | Neural-Networks | en_US |
dc.title | Improving Explainability in CNN-Based Classification of Mask Images with HayCAM plus : An Enhanced Visual Explanation Technique | en_US |
dc.type | Article | en_US |
dc.identifier.doi | 10.18280/ts.410105 | - |
dc.department | KTÜN | en_US |
dc.identifier.volume | 41 | en_US |
dc.identifier.issue | 1 | en_US |
dc.identifier.startpage | 63 | en_US |
dc.identifier.endpage | 71 | en_US |
dc.identifier.wos | WOS:001181958200002 | en_US |
dc.institutionauthor | … | - |
dc.relation.publicationcategory | Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı | en_US |
item.openairetype | Article | - |
item.cerifentitytype | Publications | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.fulltext | No Fulltext | - |
item.grantfulltext | none | - |
item.languageiso639-1 | en | - |
crisitem.author.dept | 02.04. Department of Electrical and Electronics Engineering | - |
Appears in Collections: | WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collections |
CORE Recommender
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.