Loading…

EPANet-KD: Efficient progressive attention network for fine-grained provincial village classification via knowledge distillation

Fine-grained classification of historical traditional villages plays a crucial role in guiding the future development and construction of urban and rural areas. This study aims to propose a new dataset for fine-grained classification of traditional villages and to propose an efficient progressive at...

Full description

Saved in:
Bibliographic Details
Published in:PloS one 2024-02, Vol.19 (2), p.e0298452-e0298452
Main Authors: Zhang, Cheng, Liu, Chunqing, Gong, Huimin, Teng, Jinlin
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites cdi_FETCH-LOGICAL-c559t-2f01be4fa83c83891f7aabbd8c46c84a9736d9d8afd718ccc75a62fc9f23f3b33
container_end_page e0298452
container_issue 2
container_start_page e0298452
container_title PloS one
container_volume 19
creator Zhang, Cheng
Liu, Chunqing
Gong, Huimin
Teng, Jinlin
description Fine-grained classification of historical traditional villages plays a crucial role in guiding the future development and construction of urban and rural areas. This study aims to propose a new dataset for fine-grained classification of traditional villages and to propose an efficient progressive attention network for the problem of low accuracy and efficiency of fine-grained traditional historical village classification. Firstly, in order to further study the long-standing problem of fine-grained classification of traditional villages, a new fine-grained classification dataset of traditional villages containing 4,400 images, referred to as PVCD, is proposed by crawling and hand-arranging. Secondly, a new Progressive Attention Module, abbreviated as PAM, is also proposed. PAM engages in attentional modeling of prominent spatial features within the spatial dimension, subsequently applying attentional modeling to channel features beneath the identified salient spatial features. This process involves salient spatial feature attention modeling of prominent channel features within the dimension to extract discriminative information for fine-grained classification, thereby enhancing the performance of classifying traditional villages with precision. Finally, a new knowledge distillation strategy of softened alignment distillation, or SAD for short, is proposed, which simply and efficiently transfers the knowledge of softened category probability distributions through. Notably, based on the above proposed PAM, the lightweight EPANet-Student and the heavyweight EPANet-Teacher are proposed. In addition, the heavyweight EPANet-Teacher transfers the knowledge of fine-grained categorization of traditional villages to the lightweight EPANet-Student through the proposed SAD, abbreviated as EPANet-KD. The experimental results show that the proposed EPANet-Teacher achieves state-of-the-art performance with an accuracy of 67.27%, and the proposed EPANet-KD achieves comparable performance to the proposed EPANet-Teacher with 3.32M parameters and 0.42G computation. The proposed EPANet-KD maintains a good balance of accuracy and efficiency in the fine-grained classification of traditional villages, considerably promoting the research on the fine-grained classification of traditional villages. In addition, it facilitates the digital preservation and development of traditional villages. All datasets, codes and benchmarking results are publicly available for the promotion of this
doi_str_mv 10.1371/journal.pone.0298452
format article
fullrecord <record><control><sourceid>gale_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_cca628a28c7e4292916803bcf3863621</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A782608725</galeid><doaj_id>oai_doaj_org_article_cca628a28c7e4292916803bcf3863621</doaj_id><sourcerecordid>A782608725</sourcerecordid><originalsourceid>FETCH-LOGICAL-c559t-2f01be4fa83c83891f7aabbd8c46c84a9736d9d8afd718ccc75a62fc9f23f3b33</originalsourceid><addsrcrecordid>eNqNkktv1DAUhSMEoqXwDxCKxAYWGfxIHJsNGpUBRlQU8dpaN44d3GbswfZMYcdPx-kMVUdigbywde93TqKjUxSPMZph2uIXF34THIyztXd6hojgdUPuFMdYUFIxgujdW--j4kGMFwg1lDN2vziinDYCEXRc_F58nH_QqXr_-mW5MMYqq10q18EPQcdot7qElPLIelc6na58uCyND6WxTldDgHz1E761TlkYy60dRxh0qUbI8uwH19KthfLS-atR93nZ25gmblo9LO4ZGKN-tL9Piq9vFl9O31Vn52-Xp_OzSjWNSBUxCHe6NsCp4pQLbFqAruu5qpniNYiWsl70HEzfYq6UahtgxChhCDW0o_SkWO58ew8Xch3sCsIv6cHK64EPg4SQrBq1VCpLORCuWl0TQQRmHNFOmZweZQRnr1c7r_WmW-le5XwCjAemhxtnv8vBbyVGnPG2Zdnh2d4h-B8bHZNc2ah0zsRpv4kyf5WTGglOMvp0hw6Q_80647OlmnA5bzlhiLekydTsH1Q-vV5ZlStibJ4fCJ4fCDKT9M80wCZGufz86f_Z82-HbL1jVfAxBm1uYsFITsWV--LKqbhyX9wse3I70hvR36bSPysz7gs</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2928240982</pqid></control><display><type>article</type><title>EPANet-KD: Efficient progressive attention network for fine-grained provincial village classification via knowledge distillation</title><source>Publicly Available Content Database</source><source>PubMed Central</source><creator>Zhang, Cheng ; Liu, Chunqing ; Gong, Huimin ; Teng, Jinlin</creator><contributor>Veerappampalayam Easwaramoorthy, Sathishkumar</contributor><creatorcontrib>Zhang, Cheng ; Liu, Chunqing ; Gong, Huimin ; Teng, Jinlin ; Veerappampalayam Easwaramoorthy, Sathishkumar</creatorcontrib><description>Fine-grained classification of historical traditional villages plays a crucial role in guiding the future development and construction of urban and rural areas. This study aims to propose a new dataset for fine-grained classification of traditional villages and to propose an efficient progressive attention network for the problem of low accuracy and efficiency of fine-grained traditional historical village classification. Firstly, in order to further study the long-standing problem of fine-grained classification of traditional villages, a new fine-grained classification dataset of traditional villages containing 4,400 images, referred to as PVCD, is proposed by crawling and hand-arranging. Secondly, a new Progressive Attention Module, abbreviated as PAM, is also proposed. PAM engages in attentional modeling of prominent spatial features within the spatial dimension, subsequently applying attentional modeling to channel features beneath the identified salient spatial features. This process involves salient spatial feature attention modeling of prominent channel features within the dimension to extract discriminative information for fine-grained classification, thereby enhancing the performance of classifying traditional villages with precision. Finally, a new knowledge distillation strategy of softened alignment distillation, or SAD for short, is proposed, which simply and efficiently transfers the knowledge of softened category probability distributions through. Notably, based on the above proposed PAM, the lightweight EPANet-Student and the heavyweight EPANet-Teacher are proposed. In addition, the heavyweight EPANet-Teacher transfers the knowledge of fine-grained categorization of traditional villages to the lightweight EPANet-Student through the proposed SAD, abbreviated as EPANet-KD. The experimental results show that the proposed EPANet-Teacher achieves state-of-the-art performance with an accuracy of 67.27%, and the proposed EPANet-KD achieves comparable performance to the proposed EPANet-Teacher with 3.32M parameters and 0.42G computation. The proposed EPANet-KD maintains a good balance of accuracy and efficiency in the fine-grained classification of traditional villages, considerably promoting the research on the fine-grained classification of traditional villages. In addition, it facilitates the digital preservation and development of traditional villages. All datasets, codes and benchmarking results are publicly available for the promotion of this research area. https://github.com/Jack13026212687/EPANet-KD.</description><identifier>ISSN: 1932-6203</identifier><identifier>EISSN: 1932-6203</identifier><identifier>DOI: 10.1371/journal.pone.0298452</identifier><identifier>PMID: 38359020</identifier><language>eng</language><publisher>United States: Public Library of Science</publisher><subject>Analysis ; Biology and Life Sciences ; Computer and Information Sciences ; Distribution (Probability theory) ; Evaluation ; Management ; People and Places ; Physical Sciences ; Research and Analysis Methods ; Social Sciences ; Teachers ; Villages</subject><ispartof>PloS one, 2024-02, Vol.19 (2), p.e0298452-e0298452</ispartof><rights>Copyright: © 2024 Zhang et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.</rights><rights>COPYRIGHT 2024 Public Library of Science</rights><rights>2024 Zhang et al 2024 Zhang et al</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c559t-2f01be4fa83c83891f7aabbd8c46c84a9736d9d8afd718ccc75a62fc9f23f3b33</cites><orcidid>0000-0003-2184-1565 ; 0000-0003-3279-8291</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC10868776/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC10868776/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,724,777,781,882,27905,27906,36994,53772,53774</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38359020$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><contributor>Veerappampalayam Easwaramoorthy, Sathishkumar</contributor><creatorcontrib>Zhang, Cheng</creatorcontrib><creatorcontrib>Liu, Chunqing</creatorcontrib><creatorcontrib>Gong, Huimin</creatorcontrib><creatorcontrib>Teng, Jinlin</creatorcontrib><title>EPANet-KD: Efficient progressive attention network for fine-grained provincial village classification via knowledge distillation</title><title>PloS one</title><addtitle>PLoS One</addtitle><description>Fine-grained classification of historical traditional villages plays a crucial role in guiding the future development and construction of urban and rural areas. This study aims to propose a new dataset for fine-grained classification of traditional villages and to propose an efficient progressive attention network for the problem of low accuracy and efficiency of fine-grained traditional historical village classification. Firstly, in order to further study the long-standing problem of fine-grained classification of traditional villages, a new fine-grained classification dataset of traditional villages containing 4,400 images, referred to as PVCD, is proposed by crawling and hand-arranging. Secondly, a new Progressive Attention Module, abbreviated as PAM, is also proposed. PAM engages in attentional modeling of prominent spatial features within the spatial dimension, subsequently applying attentional modeling to channel features beneath the identified salient spatial features. This process involves salient spatial feature attention modeling of prominent channel features within the dimension to extract discriminative information for fine-grained classification, thereby enhancing the performance of classifying traditional villages with precision. Finally, a new knowledge distillation strategy of softened alignment distillation, or SAD for short, is proposed, which simply and efficiently transfers the knowledge of softened category probability distributions through. Notably, based on the above proposed PAM, the lightweight EPANet-Student and the heavyweight EPANet-Teacher are proposed. In addition, the heavyweight EPANet-Teacher transfers the knowledge of fine-grained categorization of traditional villages to the lightweight EPANet-Student through the proposed SAD, abbreviated as EPANet-KD. The experimental results show that the proposed EPANet-Teacher achieves state-of-the-art performance with an accuracy of 67.27%, and the proposed EPANet-KD achieves comparable performance to the proposed EPANet-Teacher with 3.32M parameters and 0.42G computation. The proposed EPANet-KD maintains a good balance of accuracy and efficiency in the fine-grained classification of traditional villages, considerably promoting the research on the fine-grained classification of traditional villages. In addition, it facilitates the digital preservation and development of traditional villages. All datasets, codes and benchmarking results are publicly available for the promotion of this research area. https://github.com/Jack13026212687/EPANet-KD.</description><subject>Analysis</subject><subject>Biology and Life Sciences</subject><subject>Computer and Information Sciences</subject><subject>Distribution (Probability theory)</subject><subject>Evaluation</subject><subject>Management</subject><subject>People and Places</subject><subject>Physical Sciences</subject><subject>Research and Analysis Methods</subject><subject>Social Sciences</subject><subject>Teachers</subject><subject>Villages</subject><issn>1932-6203</issn><issn>1932-6203</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>DOA</sourceid><recordid>eNqNkktv1DAUhSMEoqXwDxCKxAYWGfxIHJsNGpUBRlQU8dpaN44d3GbswfZMYcdPx-kMVUdigbywde93TqKjUxSPMZph2uIXF34THIyztXd6hojgdUPuFMdYUFIxgujdW--j4kGMFwg1lDN2vziinDYCEXRc_F58nH_QqXr_-mW5MMYqq10q18EPQcdot7qElPLIelc6na58uCyND6WxTldDgHz1E761TlkYy60dRxh0qUbI8uwH19KthfLS-atR93nZ25gmblo9LO4ZGKN-tL9Piq9vFl9O31Vn52-Xp_OzSjWNSBUxCHe6NsCp4pQLbFqAruu5qpniNYiWsl70HEzfYq6UahtgxChhCDW0o_SkWO58ew8Xch3sCsIv6cHK64EPg4SQrBq1VCpLORCuWl0TQQRmHNFOmZweZQRnr1c7r_WmW-le5XwCjAemhxtnv8vBbyVGnPG2Zdnh2d4h-B8bHZNc2ah0zsRpv4kyf5WTGglOMvp0hw6Q_80647OlmnA5bzlhiLekydTsH1Q-vV5ZlStibJ4fCJ4fCDKT9M80wCZGufz86f_Z82-HbL1jVfAxBm1uYsFITsWV--LKqbhyX9wse3I70hvR36bSPysz7gs</recordid><startdate>20240215</startdate><enddate>20240215</enddate><creator>Zhang, Cheng</creator><creator>Liu, Chunqing</creator><creator>Gong, Huimin</creator><creator>Teng, Jinlin</creator><general>Public Library of Science</general><general>Public Library of Science (PLoS)</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>IOV</scope><scope>ISR</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0003-2184-1565</orcidid><orcidid>https://orcid.org/0000-0003-3279-8291</orcidid></search><sort><creationdate>20240215</creationdate><title>EPANet-KD: Efficient progressive attention network for fine-grained provincial village classification via knowledge distillation</title><author>Zhang, Cheng ; Liu, Chunqing ; Gong, Huimin ; Teng, Jinlin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c559t-2f01be4fa83c83891f7aabbd8c46c84a9736d9d8afd718ccc75a62fc9f23f3b33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Analysis</topic><topic>Biology and Life Sciences</topic><topic>Computer and Information Sciences</topic><topic>Distribution (Probability theory)</topic><topic>Evaluation</topic><topic>Management</topic><topic>People and Places</topic><topic>Physical Sciences</topic><topic>Research and Analysis Methods</topic><topic>Social Sciences</topic><topic>Teachers</topic><topic>Villages</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Cheng</creatorcontrib><creatorcontrib>Liu, Chunqing</creatorcontrib><creatorcontrib>Gong, Huimin</creatorcontrib><creatorcontrib>Teng, Jinlin</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>Gale in Context : Opposing Viewpoints</collection><collection>Gale In Context: Science</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>PloS one</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhang, Cheng</au><au>Liu, Chunqing</au><au>Gong, Huimin</au><au>Teng, Jinlin</au><au>Veerappampalayam Easwaramoorthy, Sathishkumar</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>EPANet-KD: Efficient progressive attention network for fine-grained provincial village classification via knowledge distillation</atitle><jtitle>PloS one</jtitle><addtitle>PLoS One</addtitle><date>2024-02-15</date><risdate>2024</risdate><volume>19</volume><issue>2</issue><spage>e0298452</spage><epage>e0298452</epage><pages>e0298452-e0298452</pages><issn>1932-6203</issn><eissn>1932-6203</eissn><abstract>Fine-grained classification of historical traditional villages plays a crucial role in guiding the future development and construction of urban and rural areas. This study aims to propose a new dataset for fine-grained classification of traditional villages and to propose an efficient progressive attention network for the problem of low accuracy and efficiency of fine-grained traditional historical village classification. Firstly, in order to further study the long-standing problem of fine-grained classification of traditional villages, a new fine-grained classification dataset of traditional villages containing 4,400 images, referred to as PVCD, is proposed by crawling and hand-arranging. Secondly, a new Progressive Attention Module, abbreviated as PAM, is also proposed. PAM engages in attentional modeling of prominent spatial features within the spatial dimension, subsequently applying attentional modeling to channel features beneath the identified salient spatial features. This process involves salient spatial feature attention modeling of prominent channel features within the dimension to extract discriminative information for fine-grained classification, thereby enhancing the performance of classifying traditional villages with precision. Finally, a new knowledge distillation strategy of softened alignment distillation, or SAD for short, is proposed, which simply and efficiently transfers the knowledge of softened category probability distributions through. Notably, based on the above proposed PAM, the lightweight EPANet-Student and the heavyweight EPANet-Teacher are proposed. In addition, the heavyweight EPANet-Teacher transfers the knowledge of fine-grained categorization of traditional villages to the lightweight EPANet-Student through the proposed SAD, abbreviated as EPANet-KD. The experimental results show that the proposed EPANet-Teacher achieves state-of-the-art performance with an accuracy of 67.27%, and the proposed EPANet-KD achieves comparable performance to the proposed EPANet-Teacher with 3.32M parameters and 0.42G computation. The proposed EPANet-KD maintains a good balance of accuracy and efficiency in the fine-grained classification of traditional villages, considerably promoting the research on the fine-grained classification of traditional villages. In addition, it facilitates the digital preservation and development of traditional villages. All datasets, codes and benchmarking results are publicly available for the promotion of this research area. https://github.com/Jack13026212687/EPANet-KD.</abstract><cop>United States</cop><pub>Public Library of Science</pub><pmid>38359020</pmid><doi>10.1371/journal.pone.0298452</doi><tpages>e0298452</tpages><orcidid>https://orcid.org/0000-0003-2184-1565</orcidid><orcidid>https://orcid.org/0000-0003-3279-8291</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1932-6203
ispartof PloS one, 2024-02, Vol.19 (2), p.e0298452-e0298452
issn 1932-6203
1932-6203
language eng
recordid cdi_doaj_primary_oai_doaj_org_article_cca628a28c7e4292916803bcf3863621
source Publicly Available Content Database; PubMed Central
subjects Analysis
Biology and Life Sciences
Computer and Information Sciences
Distribution (Probability theory)
Evaluation
Management
People and Places
Physical Sciences
Research and Analysis Methods
Social Sciences
Teachers
Villages
title EPANet-KD: Efficient progressive attention network for fine-grained provincial village classification via knowledge distillation
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-18T23%3A27%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=EPANet-KD:%20Efficient%20progressive%20attention%20network%20for%20fine-grained%20provincial%20village%20classification%20via%20knowledge%20distillation&rft.jtitle=PloS%20one&rft.au=Zhang,%20Cheng&rft.date=2024-02-15&rft.volume=19&rft.issue=2&rft.spage=e0298452&rft.epage=e0298452&rft.pages=e0298452-e0298452&rft.issn=1932-6203&rft.eissn=1932-6203&rft_id=info:doi/10.1371/journal.pone.0298452&rft_dat=%3Cgale_doaj_%3EA782608725%3C/gale_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c559t-2f01be4fa83c83891f7aabbd8c46c84a9736d9d8afd718ccc75a62fc9f23f3b33%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2928240982&rft_id=info:pmid/38359020&rft_galeid=A782608725&rfr_iscdi=true