Deep diffusion-invariant wasserstein distributional classification
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, S.W. | - |
dc.contributor.author | Shu, D.W. | - |
dc.contributor.author | Kwon, J. | - |
dc.date.accessioned | 2021-08-13T06:40:22Z | - |
dc.date.available | 2021-08-13T06:40:22Z | - |
dc.date.issued | 2020-12 | - |
dc.identifier.issn | 1049-5258 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/48381 | - |
dc.description.abstract | In this paper, we present a novel classification method called deep diffusion-invariant Wasserstein distributional classification (DeepWDC). DeepWDC represents input data and labels as probability measures to address severe perturbations in input data. It can output the optimal label measure in terms of diffusion invariance, where the label measure is stationary over time and becomes equivalent to a Gaussian measure. Furthermore, DeepWDC minimizes the 2-Wasserstein distance between the optimal label measure and Gaussian measure, which reduces the Wasserstein uncertainty. Experimental results demonstrate that DeepWDC can substantially enhance the accuracy of several baseline deterministic classification methods and outperforms state-of-the-art-methods on 2D and 3D data containing various types of perturbations (e.g., rotations, impulse noise, and down-scaling). © 2020 Neural information processing systems foundation. | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | Neural information processing systems foundation | - |
dc.title | Deep diffusion-invariant wasserstein distributional classification | - |
dc.type | Article | - |
dc.identifier.bibliographicCitation | Advances in Neural Information Processing Systems, v.2020-December | - |
dc.description.isOpenAccess | N | - |
dc.identifier.scopusid | 2-s2.0-85108403233 | - |
dc.citation.title | Advances in Neural Information Processing Systems | - |
dc.citation.volume | 2020-December | - |
dc.identifier.url | https://www.semanticscholar.org/paper/Deep-Diffusion-Invariant-Wasserstein-Distributional-Park-Shu/299ea9dc34543d6f2598e4bff7078727e6f0e253 | - |
dc.type.docType | Conference Paper | - |
dc.publisher.location | 미국 | - |
dc.subject.keywordPlus | Impulse noise | - |
dc.subject.keywordPlus | Input output programs | - |
dc.subject.keywordPlus | 3D data | - |
dc.subject.keywordPlus | Classification methods | - |
dc.subject.keywordPlus | Deep diffusion | - |
dc.subject.keywordPlus | Down-scaling | - |
dc.subject.keywordPlus | Gaussian measures | - |
dc.subject.keywordPlus | Input datas | - |
dc.subject.keywordPlus | Probability measures | - |
dc.subject.keywordPlus | State-of-the-art methods | - |
dc.subject.keywordPlus | Diffusion | - |
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.