Date of Graduation
5-2025
Document Type
Thesis
Degree Name
Bachelor of Science in Computer Science
Degree Level
Undergraduate
Department
Computer Science and Computer Engineering
Advisor/Mentor
Michael Gashler
Committee Member
John Gauch
Second Committee Member
Khoa Luu
Abstract
Humans infer missing visual information by focusing on spatial relationships in the context of their surroundings. Machine learning aims to replicate this skill through image completion, a fundamental task in current computer vision research. While advances in self-attention layers have recently enhanced generative machine learning models for text, these mechanisms still currently lack the capability to handle sparse image completion efficiently. We introduce a distance-based attention mechanism that uses radial-based weights to efficiently reconstruct an image. We compare this attention mechanism with self-attention and a fully connected network on an image completion task using the MNIST dataset. Our results show that the weighted spatial-attention mechanism outperformed both models, producing more accurate reconstructions with greater efficiency.
Keywords
Image Inpainting; Deep Learning; Neural Networks; Interpolation; Spatial Attention; Artificial Intelligence
Citation
Kuper, T. D. (2025). A Novel Approach to Attention-Based Models in Image Completion: Weighted Spatial-Attention Using Radial Distance. Electrical Engineering and Computer Science Undergraduate Honors Theses Retrieved from https://scholarworks.uark.edu/elcsuht/5
