Sampling based spherical transformer for 360 degree image classification
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cho, Sungmin | - |
dc.contributor.author | Jung, Raehyuk | - |
dc.contributor.author | Kwon, Junseok | - |
dc.date.accessioned | 2023-11-13T06:43:21Z | - |
dc.date.available | 2023-11-13T06:43:21Z | - |
dc.date.issued | 2024-03 | - |
dc.identifier.issn | 0957-4174 | - |
dc.identifier.issn | 1873-6793 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/68562 | - |
dc.description.abstract | Using convolutional neural networks for 360° images can induce sub-optimal performance due to distortions entailed by a planar projection. The distortion gets deteriorated when a rotation is applied to the 360° image. Thus, many researches based on convolutions attempt to reduce the distortions to learn accurate representation. In contrast, we leverage the transformer architecture to solve image classification problems for 360° images. Using the proposed transformer for 360° images has two advantages. First, our method does not require the erroneous planar projection process by sampling pixels from the sphere surface. Second, our sampling method based on regular polyhedrons makes low rotation equivariance errors, because specific rotations can be reduced to permutations of faces. In experiments, we validate our network on two aspects, as follows. First, we show that using a transformer with highly uniform sampling methods can help reduce the distortion. Second, we demonstrate that the transformer architecture can achieve rotation equivariance on specific rotations. We compare our method to other state-of-the-art algorithms using the SPH-MNIST, SPH-CIFAR, and SUN360 datasets and show that our method is competitive with other methods. © 2023 Elsevier Ltd | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | Elsevier Ltd | - |
dc.title | Sampling based spherical transformer for 360 degree image classification | - |
dc.type | Article | - |
dc.identifier.doi | 10.1016/j.eswa.2023.121853 | - |
dc.identifier.bibliographicCitation | Expert Systems with Applications, v.238 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.wosid | 001098785400001 | - |
dc.identifier.scopusid | 2-s2.0-85173262834 | - |
dc.citation.title | Expert Systems with Applications | - |
dc.citation.volume | 238 | - |
dc.type.docType | Article | - |
dc.publisher.location | 영국 | - |
dc.subject.keywordAuthor | Rotation equivariance | - |
dc.subject.keywordAuthor | Sampling method based on regular polyhedrons | - |
dc.subject.keywordAuthor | Spherical transformer | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Operations Research & Management Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Operations Research & Management Science | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194
COPYRIGHT 2019 Chung-Ang 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.