YorkSpace has migrated to a new version of its software. Access our Help Resources to learn how to use the refreshed site. Contact diginit@yorku.ca if you have any questions about the migration.
 

Top-Down Selection in Convolutional Neural Networks

Simple item page
dc.contributor.advisorTsotsos, John K.
dc.contributor.authorBiparva, Mahdi
dc.date.accessioned2020-05-11T12:46:05Z
dc.date.available2020-05-11T12:46:05Z
dc.date.copyright2019-09
dc.date.issued2020-05-11
dc.date.updated2020-05-11T12:46:05Z
dc.degree.disciplineComputer Science
dc.degree.levelDoctoral
dc.degree.namePhD - Doctor of Philosophy
dc.description.abstractFeedforward information processing fills the role of hierarchical feature encoding, transformation, reduction, and abstraction in a bottom-up manner. This paradigm of information processing is sufficient for task requirements that are satisfied in the one-shot rapid traversal of sensory information through the visual hierarchy. However, some tasks demand higher-order information processing using short-term recurrent, long-range feedback, or other processes. The predictive, corrective, and modulatory information processing in top-down fashion complement the feedforward pass to fulfill many complex task requirements. Convolutional neural networks have recently been successful in addressing some aspects of the feedforward processing. However, the role of top-down processing in such models has not yet been fully understood. We propose a top-down selection framework for convolutional neural networks to address the selective and modulatory nature of top-down processing in vision systems. We examine various aspects of the proposed model in different experimental settings such as object localization, object segmentation, task priming, compact neural representation, and contextual interference reduction. We test the hypothesis that the proposed approach is capable of accomplishing hierarchical feature localization according to task cuing. Additionally, feature modulation using the proposed approach is tested for demanding tasks such as segmentation and iterative parameter fine-tuning. Moreover, the top-down attentional traces are harnessed to enable a more compact neural representation. The experimental achievements support the practical complementary role of the top-down selection mechanisms to the bottom-up feature encoding routines.
dc.identifier.urihttps://hdl.handle.net/10315/37412
dc.languageen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subjectComputer science
dc.subject.keywordsVisual Attention
dc.subject.keywordsTop-Down Processing
dc.subject.keywordsConvolutional Neural Networks
dc.subject.keywordsDeep Learning
dc.subject.keywordsComputer Vision
dc.subject.keywordsImage Classification
dc.subject.keywordsObject Detection
dc.subject.keywordsSemantic Segmentation
dc.subject.keywordsNetwork Compression
dc.subject.keywordsTransfer Learning
dc.subject.keywordsSelective Tuning
dc.subject.keywordsRepresentation Learning
dc.titleTop-Down Selection in Convolutional Neural Networks
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Biparva_Mahdi_2019_PhD.pdf
Size:
34.96 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
license.txt
Size:
1.83 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
YorkU_ETDlicense.txt
Size:
3.36 KB
Format:
Plain Text
Description:
Download

Collections

Computer Science and Engineering

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