Addressing Data Scarcity with Computer Vision Methods

Simple item page
dc.contributor.authorDash, Amanda
dc.contributor.supervisorBranzan Albu, Alexandra
dc.date.accessioned2024-04-29T21:19:00Z
dc.date.available2024-04-29T21:19:00Z
dc.date.issued2024
dc.degree.departmentDepartment of Electrical and Computer Engineering
dc.degree.levelDoctor of Philosophy PhD
dc.description.abstractData scarcity characterizes situations where the demand for abundant, quality data is greater than their availability. Lack of quality data is a significant issue when designing and implementing computer vision-based algorithms; more specifically, deep learning-based approaches require “large” amounts of curated data for training and validation. There are many scenarios, such as environmental monitoring, where gathering more data is not viable. This dissertation explores different methodologies and strategies for overcoming data scarcity in computer vision algorithms. While addressing all methods for handling data scarcity would be an over-ambitious endeavour, this dissertation focuses on three primary strategies for working with small datasets: traditional computer vision, deep learning regularization functions, and synthetic datasets. Detailed objectives, solutions and insights from each are presented for diverse problem domains and case studies within the computer vision field. The first strategy consists of developing traditional computer vision methods. We discuss this strategy for two case studies: estimating bird population and domain-independent video summarization. The first case study results in a method that integrates motion analysis and segmentation methods to cluster and count birds in large moving flocks, filmed using hand-held video devices by citizen scientists. The second case study addresses the high demand for automatic video summarization systems due to the dramatic increase in media streaming content and consumer-level video creation; our proposed method uses a bottom-up approach for the automatic generation of dynamic video summaries by integrating motion and saliency analysis with temporal slicing. The second strategy focuses on using regularization functions while training deep learning systems. We propose a novel custom loss function, Dense Loss, which was designed to use local region homogeneity regularization to promote contiguous and smooth segmentation predictions while also using an L1-norm loss to reconstruct dense-labelled annotation ground truth for a synthetic handwritten annotation mixed-media dataset. Regularization also helps when foreground and background classes are not well-represented; we thus propose a texture-based domain-specific data augmentation technique applicable when training on small datasets for deep learning image classification tasks. The third strategy consists of generating synthetic datasets and evaluating the performance of state-of-the-art deep learning architectures when trained on them. We propose a mosaic texture dataset and an image-to-text table summarization dataset. Both address a lack of data in their corresponding application domains. Our research shows that each application domain affected by data scarcity needs to be thoroughly studied before proposing solutions to mitigate this problem. Each of the projects developed in this dissertation supports the hypothesis that small datasets are viable sources for research and applications when their particularities are addressed during development and implementation. This dissertation concludes with a set of best practices for developing Computer Vision systems with small data as a contribution to the community.
dc.description.scholarlevelGraduate
dc.identifier.urihttps://hdl.handle.net/1828/16435
dc.languageEnglisheng
dc.language.isoen
dc.rightsAvailable to the World Wide Web
dc.subjectComputer Vision
dc.subjectData scarcity
dc.subjectDeep Learning
dc.titleAddressing Data Scarcity with Computer Vision Methods
dc.typeThesis

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Amanda_Dash_PhD_Thesis___2023__Postdefense_FINAL.pdf
Size:
27.23 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.62 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Electronic Theses and Dissertations (ETD)
Theses (Electrical and Computer Engineering)
 
University of Victoria Libraries

We acknowledge and respect the Lək̓ʷəŋən (Songhees and Esquimalt) Peoples on whose territory the university stands, and the Lək̓ʷəŋən and W̱SÁNEĆ Peoples whose historical relationships with the land continue to this day.