Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.13091/3695
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Örnek, A.H. | - |
dc.contributor.author | Ceylan, M. | - |
dc.date.accessioned | 2023-03-03T13:33:36Z | - |
dc.date.available | 2023-03-03T13:33:36Z | - |
dc.date.issued | 2022 | - |
dc.identifier.isbn | 9781665488945 | - |
dc.identifier.uri | https://doi.org/10.1109/ASYU56188.2022.9925400 | - |
dc.identifier.uri | https://hdl.handle.net/20.500.13091/3695 | - |
dc.description | 2022 Innovations in Intelligent Systems and Applications Conference, ASYU 2022 -- 7 September 2022 through 9 September 2022 -- 183936 | en_US |
dc.description.abstract | Explaining how deep neural networks work is a new and challenging area for computer vision projects. The deep learning models are seen as Black-Box models because of the number of hidden layers, neurons, and activation functions. Class Activation Map (CAM) is a method that allows highlighting the most important features utilizing the last convolution layer. Since the last convolutional layer has lots of filters, it causes to create unfocused CAM outputs. Applying the Principal Component Analysis method to the filters for the purpose of uncovering the most important filters the filter size is reduced from 512 to 10 in this study. The results show that when the reduced filters are used, more focused CAMs are obtained. These maps can be used for weakly-supervised applications such as object detection and image segmentation. © 2022 IEEE. | en_US |
dc.description.sponsorship | This study was supported by ”WeSight AI-Powered Solutions” project of Huawei Turkey R&D Center. | en_US |
dc.language.iso | en | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | en_US |
dc.relation.ispartof | Proceedings - 2022 Innovations in Intelligent Systems and Applications Conference, ASYU 2022 | en_US |
dc.rights | info:eu-repo/semantics/closedAccess | en_US |
dc.subject | class activation map | en_US |
dc.subject | deep learning | en_US |
dc.subject | explainable artificial intelligence | en_US |
dc.subject | principal component analysis | en_US |
dc.subject | Activation analysis | en_US |
dc.subject | Chemical activation | en_US |
dc.subject | Convolution | en_US |
dc.subject | Deep neural networks | en_US |
dc.subject | Object detection | en_US |
dc.subject | Activation functions | en_US |
dc.subject | Activation maps | en_US |
dc.subject | Black box modelling | en_US |
dc.subject | Class activation map | en_US |
dc.subject | Deep learning | en_US |
dc.subject | Explainable artificial intelligence | en_US |
dc.subject | Hidden layer neurons | en_US |
dc.subject | Learning models | en_US |
dc.subject | Neuron functions | en_US |
dc.subject | Principal-component analysis | en_US |
dc.subject | Principal component analysis | en_US |
dc.title | A Novel Approach for Visualization of Class Activation Maps With Reduced Dimensions | en_US |
dc.type | Conference Object | en_US |
dc.identifier.doi | 10.1109/ASYU56188.2022.9925400 | - |
dc.identifier.scopus | 2-s2.0-85142760824 | - |
dc.department | KTUN | en_US |
dc.institutionauthor | … | - |
dc.relation.publicationcategory | Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı | en_US |
dc.authorscopusid | 57210593918 | - |
dc.authorscopusid | 56276648900 | - |
dc.identifier.scopusquality | N/A | - |
dc.identifier.wosquality | N/A | - |
item.fulltext | With Fulltext | - |
item.languageiso639-1 | en | - |
item.cerifentitytype | Publications | - |
item.openairetype | Conference Object | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.grantfulltext | embargo_20300101 | - |
crisitem.author.dept | 02.04. Department of Electrical and Electronics Engineering | - |
Appears in Collections: | Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collections |
Files in This Item:
File | Size | Format | |
---|---|---|---|
A_Novel_Approach_for_Visualization_of_Class_Activation_Maps_with_Reduced_Dimensions.pdf Until 2030-01-01 | 2.33 MB | Adobe PDF | View/Open Request a copy |
CORE Recommender
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.