Score-based Aggregation for Attention Modules in Image Classification Tasks
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, C | - |
dc.contributor.author | Chung, KS | - |
dc.date.accessioned | 2022-07-09T00:29:01Z | - |
dc.date.available | 2022-07-09T00:29:01Z | - |
dc.date.created | 2021-07-14 | - |
dc.date.issued | 2019-11 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/146736 | - |
dc.description.abstract | Deep Convolutional Neural Networks (CNNs) have been widely used for various computer vision tasks because they hierarchically extract bountiful features from a highdimensional image. Also, some CNNs incorporate channel attention mechanisms that re-scale each channel of intermediate feature maps based on their importance. The channel attention modules squeeze the spatial information of a feature into a representative value to transform it as a re-scaling value. In order to reduce the amount of information, attention modules have utilized hand-designed pooling functions such as max pooling or average pooling which have been widely adopted in CNNs, because they add negligible computational complexity. However, a significant amount of spatial information is lost due to these pooling functions. In this paper, we propose a generalized pooling function that scales down spatial information with respect to the importance of each pixel. Unlike max pooling or average pooling, our score-based aggregation is capable of flexibly adjusting to input. Also, the score-based aggregation function learns how to squeeze the spatial information into the must appropriate representative value, which will convert the pooling into a spatial attention mechanism. Finally, we propose a novel method called Score-based Aggregated Attention Module (SAAM) that utilizes the proposed score-based aggregation. Our experimental results on CIFAR-10 and CIFAR-100 datasets demonstrate that SAAM achieves the highest classification accuracy improvement among existing channel attention modules since the score-based aggregation in SAAM is a more dynamic and effective method than the hand-designed aggregations. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Score-based Aggregation for Attention Modules in Image Classification Tasks | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Chung, KS | - |
dc.identifier.doi | 10.1109/TIME-E47986.2019.9353302 | - |
dc.identifier.scopusid | 2-s2.0-85102410713 | - |
dc.identifier.bibliographicCitation | Proceedings of the 2019 IEEE 4th International Conference on Technology, Informatics, Management, Engineering and Environment, TIME-E 2019, pp.43 - 48 | - |
dc.relation.isPartOf | Proceedings of the 2019 IEEE 4th International Conference on Technology, Informatics, Management, Engineering and Environment, TIME-E 2019 | - |
dc.citation.title | Proceedings of the 2019 IEEE 4th International Conference on Technology, Informatics, Management, Engineering and Environment, TIME-E 2019 | - |
dc.citation.startPage | 43 | - |
dc.citation.endPage | 48 | - |
dc.type.rims | ART | - |
dc.type.docType | Conference Paper | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordPlus | Convolutional neural networks | - |
dc.subject.keywordPlus | Deep neural networks | - |
dc.subject.keywordPlus | Environmental management | - |
dc.subject.keywordPlus | Image classification | - |
dc.subject.keywordPlus | Aggregation functions | - |
dc.subject.keywordPlus | Amount of information | - |
dc.subject.keywordPlus | Attention mechanisms | - |
dc.subject.keywordPlus | Classification accuracy | - |
dc.subject.keywordPlus | High-dimensional images | - |
dc.subject.keywordPlus | Representative values | - |
dc.subject.keywordPlus | Spatial attention | - |
dc.subject.keywordPlus | Spatial informations | - |
dc.subject.keywordPlus | Classification (of information) | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/9353302 | - |
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.