Abstract
dc:description.abstractSignificant advancements in scene understanding have been driven by deep neural networks. These learning-based frameworks enhance performance through extensive training datasets and a large number of trainable parameters. However, they are less scalable and require substantial computational and financial resources. This dissertation investigates two aspects of efficient visual learning for scene understanding: label-efficient learning and parameter-efficient learning. To reduce label supervision in instance-level scene understanding tasks, we develop a series of semi-supervised learning frameworks. These frameworks improve the label efficiency under various detector architectures and unconstrained data settings. To reduce parameter usage in multi-task training, we re-evaluate parameter-efficient methods from NLP for scene understanding and then propose a more parameter-efficient method for vision architectures. These advancements demonstrate the practicality and adaptability of efficient learning frameworks in diverse, resource-constrained environments.
Degree
thesis:*- Level thesis:degree_level
- Doctoral
- Department dc:contributor.department
- Electrical and Computer Engineering
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Liu, Yen-Cheng
- Advisor dc:contributor.advisor
-
- Kira, Zsolt
- Committee members dc:contributor.committeemember
-
- Hoffman, Judy
- Heck, Larry
- Davenport, Mark
- Yang, Diyi
Subjects
dc:subject × 7Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1853/73133