Few-Shot Learning With Geometric Constraints
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jung, Hong-Gyu | - |
dc.contributor.author | Lee, Seong-Whan | - |
dc.date.accessioned | 2021-08-30T09:41:13Z | - |
dc.date.available | 2021-08-30T09:41:13Z | - |
dc.date.created | 2021-06-18 | - |
dc.date.issued | 2020-11 | - |
dc.identifier.issn | 2162-237X | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/51966 | - |
dc.description.abstract | In this article, we consider the problem of few-shot learning for classification. We assume a network trained for base categories with a large number of training examples, and we aim to add novel categories to it that have only a few, e.g., one or five, training examples. This is a challenging scenario because: 1) high performance is required in both the base and novel categories; and 2) training the network for the new categories with a few training examples can contaminate the feature space trained well for the base categories. To address these challenges, we propose two geometric constraints to fine-tune the network with a few training examples. The first constraint enables features of the novel categories to cluster near the category weights, and the second maintains the weights of the novel categories far from the weights of the base categories. By applying the proposed constraints, we extract discriminative features for the novel categories while preserving the feature space learned for the base categories. Using public data sets for few-shot learning that are subsets of ImageNet, we demonstrate that the proposed method outperforms prevalent methods by a large margin. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.subject | NEURAL-NETWORKS | - |
dc.title | Few-Shot Learning With Geometric Constraints | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Lee, Seong-Whan | - |
dc.identifier.doi | 10.1109/TNNLS.2019.2957187 | - |
dc.identifier.scopusid | 2-s2.0-85092897676 | - |
dc.identifier.wosid | 000587699700020 | - |
dc.identifier.bibliographicCitation | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, v.31, no.11, pp.4660 - 4672 | - |
dc.relation.isPartOf | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS | - |
dc.citation.title | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS | - |
dc.citation.volume | 31 | - |
dc.citation.number | 11 | - |
dc.citation.startPage | 4660 | - |
dc.citation.endPage | 4672 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Hardware & Architecture | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Theory & Methods | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.subject.keywordPlus | NEURAL-NETWORKS | - |
dc.subject.keywordAuthor | Training | - |
dc.subject.keywordAuthor | Feature extraction | - |
dc.subject.keywordAuthor | Complexity theory | - |
dc.subject.keywordAuthor | Whales | - |
dc.subject.keywordAuthor | Learning systems | - |
dc.subject.keywordAuthor | Neural networks | - |
dc.subject.keywordAuthor | Image recognition | - |
dc.subject.keywordAuthor | Deep learning | - |
dc.subject.keywordAuthor | few-shot learning | - |
dc.subject.keywordAuthor | geometric constraint | - |
dc.subject.keywordAuthor | image recognition | - |
dc.subject.keywordAuthor | neural network | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.