Multipath-DenseNet: A Supervised ensemble architecture of densely connected convolutional networks
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lodhi, Bilal | - |
dc.contributor.author | Kang, Jaewoo | - |
dc.date.accessioned | 2021-09-01T15:37:18Z | - |
dc.date.available | 2021-09-01T15:37:18Z | - |
dc.date.created | 2021-06-19 | - |
dc.date.issued | 2019-05 | - |
dc.identifier.issn | 0020-0255 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/65800 | - |
dc.description.abstract | Deep networks with skip-connections such as ResNets have achieved great results in recent years. DenseNet exploits the ResNet skip-connections by connecting each layer in convolution neural network to all preceding layers and achieves state-of-the-art accuracy. It is well-known that deeper networks are more efficient and easier to train than shallow or wider networks. Despite the high performance of very deep networks, they are limited in terms of vanishing gradient, diminishing forward flow, and slower training time. In this paper, we propose to combine the benefits of the depth and width of networks. We train supervised independent shallow networks on the same input in a block fashion. We use a state-of-the-art DenseNet block to increase the number of paths for gradient flow. Our proposed architecture has several advantages over other deeper networks including DenseNet: our architecture which we call Multipath-DenseNet is deeper as well as wider, reduces training time, and uses a smaller number of parameters. We evaluate our proposed architecture on the following four object recognition datasets: CIFAR-10, CIFAR-100, SVHN, and ImageNet. The evaluation results show that Multipath-DenseNet achieves significant improvement in performance over DenseNet on the benchmark datasets. (C) 2019 Elsevier Inc. All rights reserved. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | ELSEVIER SCIENCE INC | - |
dc.title | Multipath-DenseNet: A Supervised ensemble architecture of densely connected convolutional networks | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kang, Jaewoo | - |
dc.identifier.doi | 10.1016/j.ins.2019.01.012 | - |
dc.identifier.scopusid | 2-s2.0-85059736120 | - |
dc.identifier.wosid | 000459845900004 | - |
dc.identifier.bibliographicCitation | INFORMATION SCIENCES, v.482, pp.63 - 72 | - |
dc.relation.isPartOf | INFORMATION SCIENCES | - |
dc.citation.title | INFORMATION SCIENCES | - |
dc.citation.volume | 482 | - |
dc.citation.startPage | 63 | - |
dc.citation.endPage | 72 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.subject.keywordAuthor | Image classification | - |
dc.subject.keywordAuthor | Neural network | - |
dc.subject.keywordAuthor | Deep-learning | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
145 Anam-ro, Seongbuk-gu, Seoul, 02841, Korea+82-2-3290-2963
COPYRIGHT © 2021 Korea 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.