Modeling Semantic Correlation and Hierarchy for Real-World Wildlife Recognition
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Dong-Jin | - |
dc.contributor.author | Miao, Zhongqi | - |
dc.contributor.author | Guo, Yunhui | - |
dc.contributor.author | Yu, Stella X. | - |
dc.date.accessioned | 2023-05-09T05:32:44Z | - |
dc.date.available | 2023-05-09T05:32:44Z | - |
dc.date.created | 2023-05-03 | - |
dc.date.issued | 2023-03 | - |
dc.identifier.issn | 1070-9908 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/185467 | - |
dc.description.abstract | We explore the challenges of human-in-the-loop frameworks to label wildlife recognition datasets with a neural network. In wildlife imagery, the main challenges for a model to assist human annotation are two-fold: (1) the training dataset is usually imbalanced, which makes the model's suggestion biased, and (2) there are complex taxonomies in the classes. We establish a simple and efficient baseline, including the debiasing loss function and the hyperbolic network architecture, to address these issues. Moreover, we propose leveraging the semantic correlation to train the model more effectively by adding a co-occurrence layer to our model during training. We demonstrate the efficacy of our method in both a real-world wildlife areal survey recognition dataset and the public image classification dataset, CIFAR100-LT, CIFAR10-LT, and iNaturalist. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | Modeling Semantic Correlation and Hierarchy for Real-World Wildlife Recognition | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kim, Dong-Jin | - |
dc.identifier.doi | 10.1109/LSP.2023.3257725 | - |
dc.identifier.scopusid | 2-s2.0-85151407437 | - |
dc.identifier.wosid | 000958573100004 | - |
dc.identifier.bibliographicCitation | IEEE SIGNAL PROCESSING LETTERS, v.30, pp.259 - 263 | - |
dc.relation.isPartOf | IEEE SIGNAL PROCESSING LETTERS | - |
dc.citation.title | IEEE SIGNAL PROCESSING LETTERS | - |
dc.citation.volume | 30 | - |
dc.citation.startPage | 259 | - |
dc.citation.endPage | 263 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.subject.keywordPlus | Animals | - |
dc.subject.keywordPlus | Classification (of information) | - |
dc.subject.keywordPlus | Hyperbolic functions | - |
dc.subject.keywordPlus | Semantics | - |
dc.subject.keywordPlus | Active Learning | - |
dc.subject.keywordPlus | Class imbalance | - |
dc.subject.keywordPlus | Human annotations | - |
dc.subject.keywordPlus | Human-in-the-loop | - |
dc.subject.keywordPlus | Model semantics | - |
dc.subject.keywordPlus | Neural-networks | - |
dc.subject.keywordPlus | Real-world | - |
dc.subject.keywordPlus | Simple++ | - |
dc.subject.keywordPlus | Training dataset | - |
dc.subject.keywordPlus | Wildlife recognition | - |
dc.subject.keywordPlus | Network architecture | - |
dc.subject.keywordAuthor | Wildlife | - |
dc.subject.keywordAuthor | Training | - |
dc.subject.keywordAuthor | Neural networks | - |
dc.subject.keywordAuthor | Semantics | - |
dc.subject.keywordAuthor | Correlation | - |
dc.subject.keywordAuthor | Data models | - |
dc.subject.keywordAuthor | Birds | - |
dc.subject.keywordAuthor | Wildlife recognition | - |
dc.subject.keywordAuthor | active learning | - |
dc.subject.keywordAuthor | class imbalance | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/10073535 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
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.