Back to search

University of British Columbia

Advancing video segmentation by integrating advanced learning paradigms

Abstract

dc:description

Video segmentation involves isolating specific objects or the foreground from the background in a video, for example, separating people or vehicles from the rest of the scene. This task is crucial in many applications such as video editing, surveillance, autonomous vehicles, and augmented reality. Advanced methods often utilize Deep Learning (DL) to manage the complexities of video sequences, including motion and occlusion. Despite recent progress, current state-of-the-art methods face challenges such as catastrophic forgetting, poor domain generalization, and the loss of object details when objects are occluded by other objects. This thesis addresses these critical challenges in video segmentation by proposing innovative methodologies to enhance segmentation accuracy, robustness, and domain generalization. We introduce a Knowledge Distillation Network (KDNet) and a new training technique to combat catastrophic forgetting and improve domain generalization by leveraging advanced learning paradigms such as federated learning, continual learning, knowledge distillation, and few-shot learning. This approach yields significant improvements across diverse datasets while ensuring data privacy. Additionally, we propose a Mask Enhancement Model (MEM) to mitigate the loss of object details by integrating a foundational model output and employing mask fusion techniques, resulting in better segmentation masks. Experimental results demonstrate KDNet’s ability to achieve state-of-the art domain generalization performance on multiple datasets in foreground segmentation and adapt to new unseen domains using as few as one labelled image (one-shot learning). MEM also proves effective, versatile, and robust performance, achieving state-of-the-art results in Semi-Supervised Video Object Segmentation (S-SVOS).

Degree

thesis:*
Name thesis:degree_name
Master of Science - MSc
Level thesis:degree_level
master's
Discipline thesis:degree_discipline
Computer Science
Grantor dc:publisher
University of British Columbia
Year dc:date
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Abdelfattah, Islam
Contributors dc:contributor
  • Shehata, Mohamed S.

Rights

dc:rights
Statement dc:rights
  • Attribution-NonCommercial-NoDerivatives 4.0 International
Language dc:language
eng

Identifiers

dc:identifier.*
Handle dc:identifier
http://hdl.handle.net/2429/89330

Chain of custody

source
Harvested from
University of British Columbia
Base URL
circle.library.ubc.ca/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Abdelfattah, Islam. Advancing video segmentation by integrating advanced learning paradigms. master's thesis, University of British Columbia, 2024. http://hdl.handle.net/2429/89330