Adaptive deep learning under data scarcity

Deep learning has catalyzed transformative breakthroughs in computer vision and related fields, but these advances often rely on large-scale datasets that are neither readily accessible nor cost-effective in many real-world contexts. In many practical domains—such as medical imaging and geological mapping—collecting large-scale, expertly annotated datasets is prohibitively expensive. This thesis investigates a range of strategies designed to alleviate the pervasive challenge of data scarcity. Through comprehensive studies on both discriminative and generative tasks—including segmentation, super-resolution, modality translation, and inpainting—we demonstrate novel frameworks that preserve strong predictive performance despite limited training data. Our central goal is to show that deep learning under constrained data can still deliver robust results, provided the modeling pipelines are carefully adapted to the problem at hand. First, we propose a hierarchical diffusion-based approach that synthesizes pseudo-healthy medical images with enhanced 3D consistency but moderate computational overhead. Second, we present a fusion strategy that integrates multiple 2D diffusion models into a lightweight 3D representation, improving volumetric realism when data points are limited. Finally, we explore a multi-encoder pipeline that leverages color-space transformations to better segment complex maps, demonstrating its utility in settings like geological digitization. Taken together, these contributions illustrate that addressing data scarcity does not require sacrificing performance. Rather, it calls for more nuanced model design—incorporating domain-specific insights, ensemble architectures, and complementary data transformations. Our experiments show consistent improvements across diverse tasks, highlighting the promise of deep learning solutions that are nimble enough to excel in resource-constrained environments.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois Urbana-Champaign

Year dc:date

2025

Author dc:creator

• Kwark, Dou Hoon

Contributors dc:contributor

• Kindratenko, Volodymyr

• Deep Learning
• Data Scarcity
• Diffusion Model
• Segmentation

Statement dc:rights

• Copyright 2025 Dou Hoon Kwark

Language dc:language

en, eng

Handle dc:identifier

https://hdl.handle.net/2142/129216

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F129216