Frequency-domain deconvolution in deep learning

dc.contributor.advisorNicolls, Frederick
dc.contributor.authorMeyer, Moegamad
dc.date.accessioned2025-09-10T10:46:42Z
dc.date.available2025-09-10T10:46:42Z
dc.date.issued2025
dc.date.updated2025-09-10T10:22:26Z
dc.description.abstractThis dissertation presents an exhaustive exploration of a novel approach to deep learning in computer vision tasks: the frequency-domain deconvolution operation. Recognizing the unparalleled success of convolutional neural networks (CNNs) in the realm of computer vision, we critically evaluate the performance and computational demands of traditional convolution operations against the proposed deconvolution method. Using a systematic approach, we apply the deconvolution layer to two quintessential computer vision problems: image classification and single image super resolution (SISR). The results demonstrate the deconvolution layer's potential in certain scenarios, with marked improvements observed in image classification. For SISR tasks, though advantages were noticed under specific configurations, the traditional CNNs still demonstrated their robustness. Additionally, the dissertation touches upon the layer's computational demands, revealing an increased computational overhead for the deconvolution layer. Encouragingly, the layer demonstrated promising attributes like learning long-range filters and isolating objects from backgrounds effectively. Concluding with avenues for future research, this dissertation acts as a stepping stone in the uncharted territory of deconvolution operations, emphasising innovation alongside evaluation in the dynamic world of deep learning.
dc.identifier.apacitationMeyer, M. (2025). <i>Frequency-domain deconvolution in deep learning</i>. (). University of Cape Town ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering. Retrieved from http://hdl.handle.net/11427/41745en_ZA
dc.identifier.chicagocitationMeyer, Moegamad. <i>"Frequency-domain deconvolution in deep learning."</i> ., University of Cape Town ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering, 2025. http://hdl.handle.net/11427/41745en_ZA
dc.identifier.citationMeyer, M. 2025. Frequency-domain deconvolution in deep learning. . University of Cape Town ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering. http://hdl.handle.net/11427/41745en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Meyer, Moegamad AB - This dissertation presents an exhaustive exploration of a novel approach to deep learning in computer vision tasks: the frequency-domain deconvolution operation. Recognizing the unparalleled success of convolutional neural networks (CNNs) in the realm of computer vision, we critically evaluate the performance and computational demands of traditional convolution operations against the proposed deconvolution method. Using a systematic approach, we apply the deconvolution layer to two quintessential computer vision problems: image classification and single image super resolution (SISR). The results demonstrate the deconvolution layer's potential in certain scenarios, with marked improvements observed in image classification. For SISR tasks, though advantages were noticed under specific configurations, the traditional CNNs still demonstrated their robustness. Additionally, the dissertation touches upon the layer's computational demands, revealing an increased computational overhead for the deconvolution layer. Encouragingly, the layer demonstrated promising attributes like learning long-range filters and isolating objects from backgrounds effectively. Concluding with avenues for future research, this dissertation acts as a stepping stone in the uncharted territory of deconvolution operations, emphasising innovation alongside evaluation in the dynamic world of deep learning. DA - 2025 DB - OpenUCT DP - University of Cape Town KW - Convolutional neural networks LK - https://open.uct.ac.za PB - University of Cape Town PY - 2025 T1 - Frequency-domain deconvolution in deep learning TI - Frequency-domain deconvolution in deep learning UR - http://hdl.handle.net/11427/41745 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/41745
dc.identifier.vancouvercitationMeyer M. Frequency-domain deconvolution in deep learning. []. University of Cape Town ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering, 2025 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/41745en_ZA
dc.language.isoen
dc.language.rfc3066eng
dc.publisher.departmentDepartment of Electrical Engineering
dc.publisher.facultyFaculty of Engineering and the Built Environment
dc.publisher.institutionUniversity of Cape Town
dc.subjectConvolutional neural networks
dc.titleFrequency-domain deconvolution in deep learning
dc.typeThesis / Dissertation
dc.type.qualificationlevelMasters
dc.type.qualificationlevelMSc
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
thesis_ebe_2025_meyer moegamad.pdf
Size:
5.59 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.72 KB
Format:
Item-specific license agreed upon to submission
Description:
Collections