Active weighted mapping-based residual convolutional neural network for image classification

In visual recognition, the key to the performance improvement of ResNet is the success in establishing the stack of deep sequential convolutional layers using identical mapping by a shortcut connection. It results in multiple paths of data flow under a network and the paths are merged with the equal...

Full description

Saved in:
Bibliographic Details
Published in:Multimedia tools and applications 2021-10, Vol.80 (24), p.33139-33153
Main Authors: Jung, Hyoungho, Lee, Ryong, Lee, Sang-Hwan, Hwang, Wonjun
Format: Article
Language:English
Subjects:
Artificial neural networks
Computer Communication Networks
Computer networks
Computer Science
Data Structures and Information Theory
Image classification
Mapping
Multimedia Information Systems
Neural networks
Object recognition
Special Purpose and Application-Based Systems
Weight
Weights & measures
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c319t-227669b6b0c94a21c3f6b096cd817f10d15e197fc493f82a96743b38bc1b50c33
cites cdi_FETCH-LOGICAL-c319t-227669b6b0c94a21c3f6b096cd817f10d15e197fc493f82a96743b38bc1b50c33
container_end_page 33153
container_issue 24
container_start_page 33139
container_title Multimedia tools and applications
container_volume 80
creator Jung, Hyoungho
Lee, Ryong
Lee, Sang-Hwan
Hwang, Wonjun
description In visual recognition, the key to the performance improvement of ResNet is the success in establishing the stack of deep sequential convolutional layers using identical mapping by a shortcut connection. It results in multiple paths of data flow under a network and the paths are merged with the equal weights. However, it is questionable whether it is correct to use the fixed and predefined weights at the mapping units of all paths. In this paper, we introduce the active weighted mapping method which infers proper weight values based on the characteristic of input data on the fly. The weight values of each mapping unit are not fixed but changed as the input image is changed, and the most proper weight values for each mapping unit are derived according to the input image. For this purpose, channel-wise information is embedded from both the shortcut connection and convolutional block, and then the fully connected layers are used to estimate the weight values for the mapping units. We train the backbone network and the proposed module alternately for a more stable learning of the proposed method. Results of the extensive experiments show that the proposed method works successfully on the various backbone architectures from ResNet to DenseNet. We also verify the superiority and generality of the proposed method on various datasets in comparison with the baseline.
doi_str_mv 10.1007/s11042-020-09808-3
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2583230510</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2583230510</sourcerecordid><originalsourceid>FETCH-LOGICAL-c319t-227669b6b0c94a21c3f6b096cd817f10d15e197fc493f82a96743b38bc1b50c33</originalsourceid><addsrcrecordid>eNp9UM1KxDAYLKLguvoCngqeo9-XtE1zXBb_YMGL3oSQpknN2m3XpN3Ftze7Fbx5mhmYGYZJkmuEWwTgdwERMkqAAgFRQknYSTLDnDPCOcXTyFkJhOeA58lFCGsALHKazZL3hR7czqR745qPwdTpRm23rmtIpUJU3gRXj6pNdd_t-nYcXN9F1ZnRH2HY9_4ztb1P3UY1JtWtCsFZp9XBeZmcWdUGc_WL8-Tt4f51-URWL4_Py8WKaIZiIJTyohBVUYEWmaKomY1cFLoukVuEGnODgludCWZLqkTBM1axstJY5aAZmyc3U-_W91-jCYNc96OPQ4Okeckogxwhuujk0r4PwRsrtz6u9t8SQR5elNOLMr4ojy_KQzWbQiGau8b4v-p_Uj8lJHW2</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2583230510</pqid></control><display><type>article</type><title>Active weighted mapping-based residual convolutional neural network for image classification</title><source>ABI/INFORM Collection</source><source>Springer Link</source><creator>Jung, Hyoungho ; Lee, Ryong ; Lee, Sang-Hwan ; Hwang, Wonjun</creator><creatorcontrib>Jung, Hyoungho ; Lee, Ryong ; Lee, Sang-Hwan ; Hwang, Wonjun</creatorcontrib><description>In visual recognition, the key to the performance improvement of ResNet is the success in establishing the stack of deep sequential convolutional layers using identical mapping by a shortcut connection. It results in multiple paths of data flow under a network and the paths are merged with the equal weights. However, it is questionable whether it is correct to use the fixed and predefined weights at the mapping units of all paths. In this paper, we introduce the active weighted mapping method which infers proper weight values based on the characteristic of input data on the fly. The weight values of each mapping unit are not fixed but changed as the input image is changed, and the most proper weight values for each mapping unit are derived according to the input image. For this purpose, channel-wise information is embedded from both the shortcut connection and convolutional block, and then the fully connected layers are used to estimate the weight values for the mapping units. We train the backbone network and the proposed module alternately for a more stable learning of the proposed method. Results of the extensive experiments show that the proposed method works successfully on the various backbone architectures from ResNet to DenseNet. We also verify the superiority and generality of the proposed method on various datasets in comparison with the baseline.</description><identifier>ISSN: 1380-7501</identifier><identifier>EISSN: 1573-7721</identifier><identifier>DOI: 10.1007/s11042-020-09808-3</identifier><language>eng</language><publisher>New York: Springer US</publisher><subject>Artificial neural networks ; Computer Communication Networks ; Computer networks ; Computer Science ; Data Structures and Information Theory ; Image classification ; Mapping ; Multimedia Information Systems ; Neural networks ; Object recognition ; Special Purpose and Application-Based Systems ; Weight ; Weights &amp; measures</subject><ispartof>Multimedia tools and applications, 2021-10, Vol.80 (24), p.33139-33153</ispartof><rights>Springer Science+Business Media, LLC, part of Springer Nature 2020. corrected publication 2021</rights><rights>Springer Science+Business Media, LLC, part of Springer Nature 2020. corrected publication 2021.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c319t-227669b6b0c94a21c3f6b096cd817f10d15e197fc493f82a96743b38bc1b50c33</citedby><cites>FETCH-LOGICAL-c319t-227669b6b0c94a21c3f6b096cd817f10d15e197fc493f82a96743b38bc1b50c33</cites><orcidid>0000-0001-8895-0411</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.proquest.com/docview/2583230510/fulltextPDF?pq-origsite=primo$$EPDF$$P50$$Gproquest$$H</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/2583230510?pq-origsite=primo$$EHTML$$P50$$Gproquest$$H</linktohtml><link.rule.ids>315,786,790,11715,27957,27958,36095,44398,75252</link.rule.ids></links><search><creatorcontrib>Jung, Hyoungho</creatorcontrib><creatorcontrib>Lee, Ryong</creatorcontrib><creatorcontrib>Lee, Sang-Hwan</creatorcontrib><creatorcontrib>Hwang, Wonjun</creatorcontrib><title>Active weighted mapping-based residual convolutional neural network for image classification</title><title>Multimedia tools and applications</title><addtitle>Multimed Tools Appl</addtitle><description>In visual recognition, the key to the performance improvement of ResNet is the success in establishing the stack of deep sequential convolutional layers using identical mapping by a shortcut connection. It results in multiple paths of data flow under a network and the paths are merged with the equal weights. However, it is questionable whether it is correct to use the fixed and predefined weights at the mapping units of all paths. In this paper, we introduce the active weighted mapping method which infers proper weight values based on the characteristic of input data on the fly. The weight values of each mapping unit are not fixed but changed as the input image is changed, and the most proper weight values for each mapping unit are derived according to the input image. For this purpose, channel-wise information is embedded from both the shortcut connection and convolutional block, and then the fully connected layers are used to estimate the weight values for the mapping units. We train the backbone network and the proposed module alternately for a more stable learning of the proposed method. Results of the extensive experiments show that the proposed method works successfully on the various backbone architectures from ResNet to DenseNet. We also verify the superiority and generality of the proposed method on various datasets in comparison with the baseline.</description><subject>Artificial neural networks</subject><subject>Computer Communication Networks</subject><subject>Computer networks</subject><subject>Computer Science</subject><subject>Data Structures and Information Theory</subject><subject>Image classification</subject><subject>Mapping</subject><subject>Multimedia Information Systems</subject><subject>Neural networks</subject><subject>Object recognition</subject><subject>Special Purpose and Application-Based Systems</subject><subject>Weight</subject><subject>Weights &amp; measures</subject><issn>1380-7501</issn><issn>1573-7721</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>M0C</sourceid><recordid>eNp9UM1KxDAYLKLguvoCngqeo9-XtE1zXBb_YMGL3oSQpknN2m3XpN3Ftze7Fbx5mhmYGYZJkmuEWwTgdwERMkqAAgFRQknYSTLDnDPCOcXTyFkJhOeA58lFCGsALHKazZL3hR7czqR745qPwdTpRm23rmtIpUJU3gRXj6pNdd_t-nYcXN9F1ZnRH2HY9_4ztb1P3UY1JtWtCsFZp9XBeZmcWdUGc_WL8-Tt4f51-URWL4_Py8WKaIZiIJTyohBVUYEWmaKomY1cFLoukVuEGnODgludCWZLqkTBM1axstJY5aAZmyc3U-_W91-jCYNc96OPQ4Okeckogxwhuujk0r4PwRsrtz6u9t8SQR5elNOLMr4ojy_KQzWbQiGau8b4v-p_Uj8lJHW2</recordid><startdate>20211001</startdate><enddate>20211001</enddate><creator>Jung, Hyoungho</creator><creator>Lee, Ryong</creator><creator>Lee, Sang-Hwan</creator><creator>Hwang, Wonjun</creator><general>Springer US</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7SC</scope><scope>7WY</scope><scope>7WZ</scope><scope>7XB</scope><scope>87Z</scope><scope>8AL</scope><scope>8AO</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>8FK</scope><scope>8FL</scope><scope>8G5</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BEZIV</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FRNLG</scope><scope>F~G</scope><scope>GNUQQ</scope><scope>GUQSH</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K60</scope><scope>K6~</scope><scope>K7-</scope><scope>L.-</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>M0C</scope><scope>M0N</scope><scope>M2O</scope><scope>MBDVC</scope><scope>P5Z</scope><scope>P62</scope><scope>PQBIZ</scope><scope>PQBZA</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>Q9U</scope><orcidid>https://orcid.org/0000-0001-8895-0411</orcidid></search><sort><creationdate>20211001</creationdate><title>Active weighted mapping-based residual convolutional neural network for image classification</title><author>Jung, Hyoungho ; Lee, Ryong ; Lee, Sang-Hwan ; Hwang, Wonjun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c319t-227669b6b0c94a21c3f6b096cd817f10d15e197fc493f82a96743b38bc1b50c33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Artificial neural networks</topic><topic>Computer Communication Networks</topic><topic>Computer networks</topic><topic>Computer Science</topic><topic>Data Structures and Information Theory</topic><topic>Image classification</topic><topic>Mapping</topic><topic>Multimedia Information Systems</topic><topic>Neural networks</topic><topic>Object recognition</topic><topic>Special Purpose and Application-Based Systems</topic><topic>Weight</topic><topic>Weights &amp; measures</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Jung, Hyoungho</creatorcontrib><creatorcontrib>Lee, Ryong</creatorcontrib><creatorcontrib>Lee, Sang-Hwan</creatorcontrib><creatorcontrib>Hwang, Wonjun</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Computer and Information Systems Abstracts</collection><collection>ABI-INFORM Complete</collection><collection>ABI/INFORM Global (PDF only)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>ABI/INFORM Collection</collection><collection>Computing Database (Alumni Edition)</collection><collection>ProQuest Pharma Collection</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ABI/INFORM Collection (Alumni Edition)</collection><collection>Research Library (Alumni Edition)</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>Advanced Technologies &amp; Aerospace Database‎ (1962 - current)</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>ProQuest Business Premium Collection</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Business Premium Collection (Alumni)</collection><collection>ABI/INFORM Global (Corporate)</collection><collection>ProQuest Central Student</collection><collection>Research Library Prep</collection><collection>SciTech Premium Collection (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest Computer Science Collection</collection><collection>ProQuest Business Collection (Alumni Edition)</collection><collection>ProQuest Business Collection</collection><collection>Computer Science Database</collection><collection>ABI/INFORM Professional Advanced</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>ABI/INFORM Collection</collection><collection>Computing Database</collection><collection>ProQuest_Research Library</collection><collection>Research Library (Corporate)</collection><collection>ProQuest Advanced Technologies &amp; Aerospace Database</collection><collection>ProQuest Advanced Technologies &amp; Aerospace Collection</collection><collection>One Business</collection><collection>ProQuest One Business (Alumni)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>ProQuest Central Basic</collection><jtitle>Multimedia tools and applications</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Jung, Hyoungho</au><au>Lee, Ryong</au><au>Lee, Sang-Hwan</au><au>Hwang, Wonjun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Active weighted mapping-based residual convolutional neural network for image classification</atitle><jtitle>Multimedia tools and applications</jtitle><stitle>Multimed Tools Appl</stitle><date>2021-10-01</date><risdate>2021</risdate><volume>80</volume><issue>24</issue><spage>33139</spage><epage>33153</epage><pages>33139-33153</pages><issn>1380-7501</issn><eissn>1573-7721</eissn><abstract>In visual recognition, the key to the performance improvement of ResNet is the success in establishing the stack of deep sequential convolutional layers using identical mapping by a shortcut connection. It results in multiple paths of data flow under a network and the paths are merged with the equal weights. However, it is questionable whether it is correct to use the fixed and predefined weights at the mapping units of all paths. In this paper, we introduce the active weighted mapping method which infers proper weight values based on the characteristic of input data on the fly. The weight values of each mapping unit are not fixed but changed as the input image is changed, and the most proper weight values for each mapping unit are derived according to the input image. For this purpose, channel-wise information is embedded from both the shortcut connection and convolutional block, and then the fully connected layers are used to estimate the weight values for the mapping units. We train the backbone network and the proposed module alternately for a more stable learning of the proposed method. Results of the extensive experiments show that the proposed method works successfully on the various backbone architectures from ResNet to DenseNet. We also verify the superiority and generality of the proposed method on various datasets in comparison with the baseline.</abstract><cop>New York</cop><pub>Springer US</pub><doi>10.1007/s11042-020-09808-3</doi><tpages>15</tpages><orcidid>https://orcid.org/0000-0001-8895-0411</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 1380-7501
ispartof Multimedia tools and applications, 2021-10, Vol.80 (24), p.33139-33153
issn 1380-7501
1573-7721
language eng
recordid cdi_proquest_journals_2583230510
source ABI/INFORM Collection; Springer Link
subjects Artificial neural networks
Computer Communication Networks
Computer networks
Computer Science
Data Structures and Information Theory
Image classification
Mapping
Multimedia Information Systems
Neural networks
Object recognition
Special Purpose and Application-Based Systems
Weight
Weights & measures
title Active weighted mapping-based residual convolutional neural network for image classification
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-23T07%3A33%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Active%20weighted%20mapping-based%20residual%20convolutional%20neural%20network%20for%20image%20classification&rft.jtitle=Multimedia%20tools%20and%20applications&rft.au=Jung,%20Hyoungho&rft.date=2021-10-01&rft.volume=80&rft.issue=24&rft.spage=33139&rft.epage=33153&rft.pages=33139-33153&rft.issn=1380-7501&rft.eissn=1573-7721&rft_id=info:doi/10.1007/s11042-020-09808-3&rft_dat=%3Cproquest_cross%3E2583230510%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c319t-227669b6b0c94a21c3f6b096cd817f10d15e197fc493f82a96743b38bc1b50c33%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2583230510&rft_id=info:pmid/&rfr_iscdi=true