Class Activation Mapping-Driven Data Augmentation: Masking Significant Regions for Enhanced Acoustic Scene Classification
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Byun, Pil Moo | - |
dc.contributor.author | Choi, Jeong-Hwan | - |
dc.contributor.author | Chang, Joon-Hyuk | - |
dc.date.accessioned | 2023-11-14T08:23:41Z | - |
dc.date.available | 2023-11-14T08:23:41Z | - |
dc.date.created | 2023-10-16 | - |
dc.date.issued | 2023-10 | - |
dc.identifier.issn | 1931-1168 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/192210 | - |
dc.description.abstract | This paper proposes a novel masking augmentation method for acoustic scene data using class activation mapping (CAM) to improve the performance of audio scene classification (ASC) tasks. CAM enables the identification of significant regions within the input data by emphasizing areas exhibiting the strongest activation, obtained through gradients resulting from backpropagation with respect to specific classes. By masking these important regions identified by CAM, discriminative features can be learned from less important areas, thereby mitigating the overfitting to the important regions. The proposed augmentation method promotes deep learning model robustness and generalization, and mitigates potential performance fluctuations caused by random masking. Furthermore, we investigate various masking shapes, such as rectangular, cross-shaped, and circular masks. Experimental results on the DCASE challenge 2019 Dataset demonstrate that applying masking techniques based on CAM algorithms leads to superior ASC accuracy compared to SpecAugment, which is the most widely used masking augmentation method in combination with two ResNet-based model architectures. This study highlights the potential of CAM-driven data augmentation in the ASC domain and provides valuable insights for future research and development in the field. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Class Activation Mapping-Driven Data Augmentation: Masking Significant Regions for Enhanced Acoustic Scene Classification | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Chang, Joon-Hyuk | - |
dc.identifier.doi | 10.1109/WASPAA58266.2023.10248147 | - |
dc.identifier.scopusid | 2-s2.0-85173053597 | - |
dc.identifier.wosid | 001073615200052 | - |
dc.identifier.bibliographicCitation | IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, v.2023-October, pp.1 - 5 | - |
dc.relation.isPartOf | IEEE Workshop on Applications of Signal Processing to Audio and Acoustics | - |
dc.citation.title | IEEE Workshop on Applications of Signal Processing to Audio and Acoustics | - |
dc.citation.volume | 2023-October | - |
dc.citation.startPage | 1 | - |
dc.citation.endPage | 5 | - |
dc.type.rims | ART | - |
dc.type.docType | Proceedings Paper | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Acoustics | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Acoustics | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.subject.keywordPlus | Audio acoustics | - |
dc.subject.keywordPlus | Cams | - |
dc.subject.keywordPlus | Deep learning | - |
dc.subject.keywordPlus | Mapping | - |
dc.subject.keywordPlus | Chemical activation | - |
dc.subject.keywordPlus | Activation mapping | - |
dc.subject.keywordPlus | Activation maps | - |
dc.subject.keywordPlus | Audio scene classification | - |
dc.subject.keywordPlus | Audio scenes | - |
dc.subject.keywordPlus | Augmentation methods | - |
dc.subject.keywordPlus | Class activation map | - |
dc.subject.keywordPlus | Data augmentation | - |
dc.subject.keywordPlus | Masking | - |
dc.subject.keywordPlus | Performance | - |
dc.subject.keywordPlus | Scene classification | - |
dc.subject.keywordAuthor | audio scene classification | - |
dc.subject.keywordAuthor | class activation maps | - |
dc.subject.keywordAuthor | data augmentation | - |
dc.subject.keywordAuthor | masking | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/10248147 | - |
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.