Back to search

University of British Columbia

Learning efficient representations for generalizable segmentation in data-limited scenarios

Abstract

dc:description

Adapting visual recognition models to novel categories with minimal supervision is important, especially for dense prediction tasks like segmentation, where collecting pixel-level annotations is costly or impractical. These challenges are greater in data-limited domains and under distribution shifts, requiring models that can generalize with limited supervision. This thesis focuses on learning efficient representations to enable such generalization. We present three key contributions. First, motivated by how humans use global context in visual reasoning, we propose an object-centric global reasoning module that aggregates semantically similar features into latent tokens representing object instances or parts. These tokens interact through a global reasoning mechanism to enhance contextual understanding without requiring additional instance-level annotations. Second, we address generalized few-shot segmentation, aiming to adapt to novel classes from few examples while preserving performance on base categories learned with abundant data. We introduce learnable visual prompts and a causal cross-attention mechanism that contextualizes novel class prompts relative to base classes, while a transductive prompt-tuning strategy leverages unlabeled test images to improve test-time performance. Finally, we investigate training-free, open-vocabulary segmentation using vision-language models (VLMs) and propose an unsupervised entropy-based metric, InfoScore, to automatically select the most effective attention layers for segmentation. Our method generalizes across diverse VLM architectures and shows that minimal visual supervision—such as a single example per category—can significantly improve segmentation by reducing the semantic gap between class names and visual representations. Together, these contributions advance segmentation techniques toward scalable, adaptable solutions for data-limited and low-supervision settings.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy - PhD
Level thesis:degree_level
doctoral
Discipline thesis:degree_discipline
Computer Science
Grantor dc:publisher
University of British Columbia
Year dc:date
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Hossain, Mir Rayat Imtiaz
Contributors dc:contributor
  • Sigal, Leonid
  • Little, James Joseph, 1951-

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/2429/92710

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

Hossain, Mir Rayat Imtiaz. Learning efficient representations for generalizable segmentation in data-limited scenarios. doctoral thesis, University of British Columbia, 2025. http://hdl.handle.net/2429/92710