TrSeg: Transformer for semantic segmentation
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jin, Y. | - |
dc.contributor.author | Han, D. | - |
dc.contributor.author | Ko, H. | - |
dc.date.accessioned | 2022-03-05T22:40:34Z | - |
dc.date.available | 2022-03-05T22:40:34Z | - |
dc.date.created | 2022-02-15 | - |
dc.date.issued | 2021 | - |
dc.identifier.issn | 0167-8655 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/137913 | - |
dc.description.abstract | Recent efforts in semantic segmentation using deep learning frameworks have made notable advances. However, capturing the existence of objects in an image at multiple scales still remains a challenge. In this paper, we address the semantic segmentation task based on transformer architecture. Unlike existing methods that capture multi-scale contextual information through infusing every single-scale piece of information from parallel paths, we propose a novel semantic segmentation network incorporating a transformer (TrSeg) to adaptively capture multi-scale information with the dependencies on original contextual information. Given the original contextual information as keys and values, the multi-scale contextual information from the multi-scale pooling module as queries is transformed by the transformer decoder. The experimental results show that TrSeg outperforms the other methods of capturing multi-scale information by large margins. © 2021 Elsevier B.V. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | Elsevier B.V. | - |
dc.title | TrSeg: Transformer for semantic segmentation | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Ko, H. | - |
dc.identifier.doi | 10.1016/j.patrec.2021.04.024 | - |
dc.identifier.scopusid | 2-s2.0-85106916179 | - |
dc.identifier.bibliographicCitation | Pattern Recognition Letters, v.148, pp.29 - 35 | - |
dc.relation.isPartOf | Pattern Recognition Letters | - |
dc.citation.title | Pattern Recognition Letters | - |
dc.citation.volume | 148 | - |
dc.citation.startPage | 29 | - |
dc.citation.endPage | 35 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordAuthor | Multi-scale contextual information | - |
dc.subject.keywordAuthor | Scene understanding | - |
dc.subject.keywordAuthor | Semantic segmentation | - |
dc.subject.keywordAuthor | Transformer | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
145 Anam-ro, Seongbuk-gu, Seoul, 02841, Korea+82-2-3290-2963
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.