EfficientNet-EA for Visual Location Recognition in Natural Scenes
In natural scenarios, the visual location recognition often experiences reduced accuracy because of variations in weather, lighting, camera angles, and occlusions caused by dynamic objects. This paper introduces an EfficientNet-EA-based algorithm specifically designed to tackle these challenges. The...
Gespeichert in:
| Veröffentlicht in: | IEEE robotics and automation letters 2025-01, Vol.10 (1), p.596-603 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 603 |
|---|---|
| container_issue | 1 |
| container_start_page | 596 |
| container_title | IEEE robotics and automation letters |
| container_volume | 10 |
| creator | Zhang, Heng Chen, Yanchao Liu, Yanli |
| description | In natural scenarios, the visual location recognition often experiences reduced accuracy because of variations in weather, lighting, camera angles, and occlusions caused by dynamic objects. This paper introduces an EfficientNet-EA-based algorithm specifically designed to tackle these challenges. The algorithm enhances its capabilities by appending the Efficient Feature Aggregation (EA) layer to the end of EfficientNet and by using MultiSimilarityLoss for training purposes. This design enhances the model's ability to extract features, thereby boosting efficiency and accuracy. During the training phase, the model adeptly identifies and utilizes hard-negative and challenging positive samples, which in turn enhances its training efficacy and generalizability across diverse situations. The experimental results indicate that EfficientNet-EA achieves a recall@10 of 98.6% on Pitts30k-test. The model demonstrates a certain degree of improvement in recognition rates under weather variations, changes in illumination, shifts in perspective, and the presence of dynamic object occlusions. |
| doi_str_mv | 10.1109/LRA.2024.3511379 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_LRA_2024_3511379</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10777584</ieee_id><sourcerecordid>3143028560</sourcerecordid><originalsourceid>FETCH-LOGICAL-c175t-f07e610609bf3c2ed2c911c4e58104f49d4fdca82280947b17981fe3c23a5b4a3</originalsourceid><addsrcrecordid>eNpNkD1rwzAQhkVpoSHN3qGDobPdO31Y1mhC-gEmhfRjFYoiFYXUTiV76L-v02TIdC_c897BQ8gtQoEI6qFZ1QUFygsmEJlUF2RCmZQ5k2V5eZavySylLQCgoJIpMSH1wvtgg2v7pevzRZ35LmafIQ1mlzWdNX3o2mzlbPfVhv8c2mxp-iGO-zfrWpduyJU3u-RmpzklH4-L9_lz3rw-vczrJrcoRZ97kK5EKEGtPbPUbahViJY7USFwz9WG-401FaUVKC7XKFWF3o0oM2LNDZuS--Pdfex-Bpd6ve2G2I4vNUPOgFaihJGCI2Vjl1J0Xu9j-DbxVyPogys9utIHV_rkaqzcHSvBOXeGSylFxdkfsaZjTg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3143028560</pqid></control><display><type>article</type><title>EfficientNet-EA for Visual Location Recognition in Natural Scenes</title><source>IEEE Electronic Library (IEL)</source><creator>Zhang, Heng ; Chen, Yanchao ; Liu, Yanli</creator><creatorcontrib>Zhang, Heng ; Chen, Yanchao ; Liu, Yanli</creatorcontrib><description>In natural scenarios, the visual location recognition often experiences reduced accuracy because of variations in weather, lighting, camera angles, and occlusions caused by dynamic objects. This paper introduces an EfficientNet-EA-based algorithm specifically designed to tackle these challenges. The algorithm enhances its capabilities by appending the Efficient Feature Aggregation (EA) layer to the end of EfficientNet and by using MultiSimilarityLoss for training purposes. This design enhances the model's ability to extract features, thereby boosting efficiency and accuracy. During the training phase, the model adeptly identifies and utilizes hard-negative and challenging positive samples, which in turn enhances its training efficacy and generalizability across diverse situations. The experimental results indicate that EfficientNet-EA achieves a recall@10 of 98.6% on Pitts30k-test. The model demonstrates a certain degree of improvement in recognition rates under weather variations, changes in illumination, shifts in perspective, and the presence of dynamic object occlusions.</description><identifier>ISSN: 2377-3766</identifier><identifier>EISSN: 2377-3766</identifier><identifier>DOI: 10.1109/LRA.2024.3511379</identifier><identifier>CODEN: IRALC6</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Accuracy ; Algorithms ; Computational modeling ; Convolutional neural networks ; EA layer ; EfficientNet-EA ; Feature extraction ; Illumination ; Image recognition ; Lighting ; Meteorology ; multisimilarityloss function ; Semantics ; Training ; Visual location recognition ; Visualization ; Weather</subject><ispartof>IEEE robotics and automation letters, 2025-01, Vol.10 (1), p.596-603</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c175t-f07e610609bf3c2ed2c911c4e58104f49d4fdca82280947b17981fe3c23a5b4a3</cites><orcidid>0000-0001-9027-3261 ; 0000-0002-2691-034X ; 0009-0006-2873-1069</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10777584$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10777584$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Zhang, Heng</creatorcontrib><creatorcontrib>Chen, Yanchao</creatorcontrib><creatorcontrib>Liu, Yanli</creatorcontrib><title>EfficientNet-EA for Visual Location Recognition in Natural Scenes</title><title>IEEE robotics and automation letters</title><addtitle>LRA</addtitle><description>In natural scenarios, the visual location recognition often experiences reduced accuracy because of variations in weather, lighting, camera angles, and occlusions caused by dynamic objects. This paper introduces an EfficientNet-EA-based algorithm specifically designed to tackle these challenges. The algorithm enhances its capabilities by appending the Efficient Feature Aggregation (EA) layer to the end of EfficientNet and by using MultiSimilarityLoss for training purposes. This design enhances the model's ability to extract features, thereby boosting efficiency and accuracy. During the training phase, the model adeptly identifies and utilizes hard-negative and challenging positive samples, which in turn enhances its training efficacy and generalizability across diverse situations. The experimental results indicate that EfficientNet-EA achieves a recall@10 of 98.6% on Pitts30k-test. The model demonstrates a certain degree of improvement in recognition rates under weather variations, changes in illumination, shifts in perspective, and the presence of dynamic object occlusions.</description><subject>Accuracy</subject><subject>Algorithms</subject><subject>Computational modeling</subject><subject>Convolutional neural networks</subject><subject>EA layer</subject><subject>EfficientNet-EA</subject><subject>Feature extraction</subject><subject>Illumination</subject><subject>Image recognition</subject><subject>Lighting</subject><subject>Meteorology</subject><subject>multisimilarityloss function</subject><subject>Semantics</subject><subject>Training</subject><subject>Visual location recognition</subject><subject>Visualization</subject><subject>Weather</subject><issn>2377-3766</issn><issn>2377-3766</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2025</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkD1rwzAQhkVpoSHN3qGDobPdO31Y1mhC-gEmhfRjFYoiFYXUTiV76L-v02TIdC_c897BQ8gtQoEI6qFZ1QUFygsmEJlUF2RCmZQ5k2V5eZavySylLQCgoJIpMSH1wvtgg2v7pevzRZ35LmafIQ1mlzWdNX3o2mzlbPfVhv8c2mxp-iGO-zfrWpduyJU3u-RmpzklH4-L9_lz3rw-vczrJrcoRZ97kK5EKEGtPbPUbahViJY7USFwz9WG-401FaUVKC7XKFWF3o0oM2LNDZuS--Pdfex-Bpd6ve2G2I4vNUPOgFaihJGCI2Vjl1J0Xu9j-DbxVyPogys9utIHV_rkaqzcHSvBOXeGSylFxdkfsaZjTg</recordid><startdate>202501</startdate><enddate>202501</enddate><creator>Zhang, Heng</creator><creator>Chen, Yanchao</creator><creator>Liu, Yanli</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0001-9027-3261</orcidid><orcidid>https://orcid.org/0000-0002-2691-034X</orcidid><orcidid>https://orcid.org/0009-0006-2873-1069</orcidid></search><sort><creationdate>202501</creationdate><title>EfficientNet-EA for Visual Location Recognition in Natural Scenes</title><author>Zhang, Heng ; Chen, Yanchao ; Liu, Yanli</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c175t-f07e610609bf3c2ed2c911c4e58104f49d4fdca82280947b17981fe3c23a5b4a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2025</creationdate><topic>Accuracy</topic><topic>Algorithms</topic><topic>Computational modeling</topic><topic>Convolutional neural networks</topic><topic>EA layer</topic><topic>EfficientNet-EA</topic><topic>Feature extraction</topic><topic>Illumination</topic><topic>Image recognition</topic><topic>Lighting</topic><topic>Meteorology</topic><topic>multisimilarityloss function</topic><topic>Semantics</topic><topic>Training</topic><topic>Visual location recognition</topic><topic>Visualization</topic><topic>Weather</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Heng</creatorcontrib><creatorcontrib>Chen, Yanchao</creatorcontrib><creatorcontrib>Liu, Yanli</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE robotics and automation letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zhang, Heng</au><au>Chen, Yanchao</au><au>Liu, Yanli</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>EfficientNet-EA for Visual Location Recognition in Natural Scenes</atitle><jtitle>IEEE robotics and automation letters</jtitle><stitle>LRA</stitle><date>2025-01</date><risdate>2025</risdate><volume>10</volume><issue>1</issue><spage>596</spage><epage>603</epage><pages>596-603</pages><issn>2377-3766</issn><eissn>2377-3766</eissn><coden>IRALC6</coden><abstract>In natural scenarios, the visual location recognition often experiences reduced accuracy because of variations in weather, lighting, camera angles, and occlusions caused by dynamic objects. This paper introduces an EfficientNet-EA-based algorithm specifically designed to tackle these challenges. The algorithm enhances its capabilities by appending the Efficient Feature Aggregation (EA) layer to the end of EfficientNet and by using MultiSimilarityLoss for training purposes. This design enhances the model's ability to extract features, thereby boosting efficiency and accuracy. During the training phase, the model adeptly identifies and utilizes hard-negative and challenging positive samples, which in turn enhances its training efficacy and generalizability across diverse situations. The experimental results indicate that EfficientNet-EA achieves a recall@10 of 98.6% on Pitts30k-test. The model demonstrates a certain degree of improvement in recognition rates under weather variations, changes in illumination, shifts in perspective, and the presence of dynamic object occlusions.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/LRA.2024.3511379</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0001-9027-3261</orcidid><orcidid>https://orcid.org/0000-0002-2691-034X</orcidid><orcidid>https://orcid.org/0009-0006-2873-1069</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2377-3766 |
| ispartof | IEEE robotics and automation letters, 2025-01, Vol.10 (1), p.596-603 |
| issn | 2377-3766 2377-3766 |
| language | eng |
| recordid | cdi_crossref_primary_10_1109_LRA_2024_3511379 |
| source | IEEE Electronic Library (IEL) |
| subjects | Accuracy Algorithms Computational modeling Convolutional neural networks EA layer EfficientNet-EA Feature extraction Illumination Image recognition Lighting Meteorology multisimilarityloss function Semantics Training Visual location recognition Visualization Weather |
| title | EfficientNet-EA for Visual Location Recognition in Natural Scenes |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-06T23%3A52%3A22IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=EfficientNet-EA%20for%20Visual%20Location%20Recognition%20in%20Natural%20Scenes&rft.jtitle=IEEE%20robotics%20and%20automation%20letters&rft.au=Zhang,%20Heng&rft.date=2025-01&rft.volume=10&rft.issue=1&rft.spage=596&rft.epage=603&rft.pages=596-603&rft.issn=2377-3766&rft.eissn=2377-3766&rft.coden=IRALC6&rft_id=info:doi/10.1109/LRA.2024.3511379&rft_dat=%3Cproquest_RIE%3E3143028560%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3143028560&rft_id=info:pmid/&rft_ieee_id=10777584&rfr_iscdi=true |