Progressive Hierarchical Classification For Multi-Category Image Classification

Simple item page
dc.contributor.advisorChen, Stephen
dc.contributor.authorKuo, Te-Chuan
dc.date.accessioned2024-10-28T13:37:27Z
dc.date.available2024-10-28T13:37:27Z
dc.date.copyright2024-08-01
dc.date.issued2024-10-28
dc.date.updated2024-10-28T13:37:27Z
dc.degree.disciplineInformation Systems and Technology
dc.degree.levelMaster's
dc.degree.nameMA - Master of Arts
dc.description.abstractThis thesis evaluates a hierarchical classification model applied to the CIFAR-10 dataset, focusing on addressing the limitations of existing methods, which often struggle with (i) overlapping features and (ii) poor interpretability of classification decisions. The hierarchical model was implemented to mitigate these issues by refining classification through a multi-stage process that narrows the focus progressively. Our hierarchical approach has demonstrated its ability to focus on distinguishing features critical to specific classes and groups/pairs. Furthermore, the hierarchical models provide enhanced transparency over the baseline model by allowing a granular examination of classification performance across multiple stages.
dc.identifier.urihttps://hdl.handle.net/10315/42385
dc.languageen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subjectInformation technology
dc.subjectComputer science
dc.subject.keywordsHierarchical classification
dc.subject.keywordsImage classification
dc.subject.keywordsTrustworthy AI
dc.subject.keywordsConvolutional neural networks
dc.subject.keywordsDivide-and-conquer
dc.titleProgressive Hierarchical Classification For Multi-Category Image Classification
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Te-Chuan_Kuo_2024_Master.pdf
Size:
2.1 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
license.txt
Size:
1.87 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
YorkU_ETDlicense.txt
Size:
3.39 KB
Format:
Plain Text
Description:
Download

Collections

Information Systems and Technology

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.