Abstract
dc:description.abstractComputer vision has made significant progress in the past decade, primarily due to the dominant supervised learning paradigm, which involves training large-scale neural networks on extensive datasets for each task. However, scalable data and annotation collection often prove to be intractable. In contrast, humans can adapt to new vision tasks with very little data or few labels. This thesis aims to bridge this gap by presenting a practical solution: pre-training deep neural networks on accessible large-scale internet images, and then employing various techniques to adapt these pre-trained models to diverse downstream tasks with minimal or no additional data. In the pre-training stage, I introduce two meta-learning methods to achieve better pre-trained image representations that generalize to novel classes with minimal extra annotations. In the adaptation stage, I demonstrate multiple techniques for effectively adapting pre-trained models to data-constrained downstream tasks such as recognition, dense prediction, 3D generation, and reference-based image completion.
Degree
thesis:*- Name thesis:degree_name
- Ph. D., Computer Science
- Level thesis:degree_level
- Doctor of Philosophy
- Discipline thesis:degree_discipline
- Computer Science
- Grantor
- Cornell University
- Year dc:date.issued
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Tang, Luming
- Chair dc:contributor.chair
-
- Hariharan, Bharath
- Committee members dc:contributor.committeemember
-
- Marschner, Stephen
- Snavely, Keith
Subjects
dc:subject × 4Rights
dc:rights- Statement dc:rights
-
- Attribution-NonCommercial 4.0 International
- Licence dc:rights.uri
- Language dc:language.iso
- en
Identifiers
dc:identifier.*- Dc Identifier Bibid
- 16611759
- Dc Identifier Other
-
ProQuest Submission ID: 14373
ProQuest Publication ID: 31331535