Back to search
University of Alabama Birmingham
The Efficacy of Weakly Supervised Learning for Biomedical Imaging
Abstract
dc:description.abstractThis paper aims to investigate the use of unsupervised saliency proposals in extracting suitable prior information from computed tomography scans of the head using image-level labels. The weak supervision learning method obtains useful information about an object’s location and fuses this result with an unsupervised saliency proposal to propagate labels to all related pixels. However, it is shown that unsupervised saliency guidance fails to supply the synthetic annotations with enough coherence to produce suitable segmentation.
Degree
thesis:*- Level thesis:degree_level
- Thesis
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Hatcher, Solomon Lee
- Contributors dc:contributor
-
- Leon Jololian
- Frank M Skidmore
- Despina Stavrinos
Subjects
dc:subject × 7Identifiers
dc:identifier.*- Repository record dc:identifier
- https://digitalcommons.library.uab.edu/etd-collection/1892