Georgia Institute of Technology
Low-shot learning for object recognition, detection, and segmentation
Abstract
dc:description.abstractDeep Neural Networks are powerful at solving classification problems in computer vision. However, learning classifiers with these models requires a large amount of labeled training data, and recent approaches have struggled to adapt to new classes in a data-efficient manner. On the other hand, the human brain is capable of utilizing already known knowledge in order to learn new concepts with fewer examples and less supervision. Many meta-learning algorithms have been proposed to fill this gap but they come with their practical and theoretical limitations. We review the well-known bi-level optimization as a general framework for few-shot learning and hyperparameter optimization and discuss the practical limitations of computing the full gradient. We provide theoretical guarantees for the convergence of the bi-level optimization using the approximated gradients computed by the truncated back-propagation. In the next step, we propose an empirical method for few-shot semantic segmentation: instead of solving the inner optimization, we propose to directly estimate its result by a general function approximator. Finally, we will discuss extensions of this work with the focus on weakly-supervised object detection when full supervision is not available for the few training examples.
Degree
thesis:*- Level thesis:degree_level
- Doctoral
- Department dc:contributor.department
- Interactive Computing
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2020
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Shaban, Amirreza
- Advisor dc:contributor.advisor
-
- Boots, Byron
- Committee members dc:contributor.committeemember
-
- Hays, James
- Batra, Dhruv
- Kira, Zsolt
- Li, Fuxin
Subjects
dc:subject × 6Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- http://hdl.handle.net/1853/63599