Autoencoding Under Normalization Constraints
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yoon, Sangwoong | - |
dc.contributor.author | Noh, Yung-Kyun | - |
dc.contributor.author | Park, Frank C. | - |
dc.date.accessioned | 2022-07-06T16:06:31Z | - |
dc.date.available | 2022-07-06T16:06:31Z | - |
dc.date.created | 2022-05-04 | - |
dc.date.issued | 2021-07 | - |
dc.identifier.issn | 2640-3498 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/141471 | - |
dc.description.abstract | Likelihood is a standard estimate for outlier detection. The specific role of the normalization constraint is to ensure that the out-of-distribution (OOD) regime has a small likelihood when samples are learned using maximum likelihood. Because autoencoders do not possess such a process of normalization, they often fail to recognize outliers even when they are obviously OOD. We propose the Normalized Autoencoder (NAE), a normalized pro-babilistic model constructed from an autoencoder. The probability density of NAE is defined using the reconstruction error of an autoencoder, which is differently defined in the conventional energy-based model. In our model, normalization is enforced by suppressing the reconstruction of negative samples, significantly improving the outlier detection performance. Our experimental results confirm the efficacy of NAE, both in detecting outliers and in generating in-distribution samples. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | JMLR-JOURNAL MACHINE LEARNING RESEARCH | - |
dc.title | Autoencoding Under Normalization Constraints | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Noh, Yung-Kyun | - |
dc.identifier.doi | 10.48550/arXiv.2105.05735 | - |
dc.identifier.scopusid | 2-s2.0-85161287114 | - |
dc.identifier.wosid | 000768182702019 | - |
dc.identifier.bibliographicCitation | INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, v.139, pp.12087 - 12097 | - |
dc.relation.isPartOf | INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139 | - |
dc.citation.title | INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139 | - |
dc.citation.volume | 139 | - |
dc.citation.startPage | 12087 | - |
dc.citation.endPage | 12097 | - |
dc.type.rims | ART | - |
dc.type.docType | Proceedings Paper | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.subject.keywordPlus | NOVELTY DETECTION | - |
dc.identifier.url | https://proceedings.mlr.press/v139/yoon21c.html | - |
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.