Positive-Incentive Pseudo Label Optimization for Salient Object Detection
We present a salient object detection method in this paper. It uses a lightweight network based on multi-scale information aggregation (MIA) module and bidirectional cross-stage feature fusion (BCF2) module to speed up the reasoning process. Besides, it designs a stepwise coupling optimization strat...
Gespeichert in:
| Veröffentlicht in: | IEEE access 2024, Vol.12, p.153841-153850 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 153850 |
|---|---|
| container_issue | |
| container_start_page | 153841 |
| container_title | IEEE access |
| container_volume | 12 |
| creator | Fang, Jie Zhang, Weitao Zhang, Shasha Wang, Nan |
| description | We present a salient object detection method in this paper. It uses a lightweight network based on multi-scale information aggregation (MIA) module and bidirectional cross-stage feature fusion (BCF2) module to speed up the reasoning process. Besides, it designs a stepwise coupling optimization strategy based on positive-incentive pseudo label to alleviate the miss detection rate for small objects and the false detection rate for big objects. It is worth noting that the positive-incentive pseudo label generation mechanism can increase the ratio of salient pixels in small objects to alleviate the severe category imbalance problem, while the stepwise coupling optimization strategy can avoid the misguidance of pseudo label to big objects. In addition, the experimental results demonstrate that our method is fairly efficient, its frame rate in reasoning phase reaches 275.6 FPS on NVIDIA RTX3080 GPU when the input resolution is set to 336\times 336 . |
| doi_str_mv | 10.1109/ACCESS.2024.3476077 |
| format | Article |
| fullrecord | <record><control><sourceid>doaj_ieee_</sourceid><recordid>TN_cdi_ieee_primary_10707262</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10707262</ieee_id><doaj_id>oai_doaj_org_article_b3087411048b4f6ebf18980cb8bb2b54</doaj_id><sourcerecordid>oai_doaj_org_article_b3087411048b4f6ebf18980cb8bb2b54</sourcerecordid><originalsourceid>FETCH-LOGICAL-c261t-5f8b38d1f986dc398ee6daa7231353c106a48dac29b428b160606c99c15131b33</originalsourceid><addsrcrecordid>eNpNkNtKw0AQhhdRsNQ-gV7kBVL3lD1cllg1UGiher3sbiayJe2WJAr69G5Nkc5czDAz_8_wIXRP8JwQrB8XZbncbucUUz5nXAos5RWaUCJ0zgomri_6WzTr-x1OodKokBNUbWIfhvAFeXXwcDh12aaHzzpmK-ugzdbHIezDjx1CPGRN7LKtbUM6zNZuB37InmBIJS3v0E1j2x5m5zpF78_Lt_I1X61fqnKxyj0VZMiLRjmmatJoJWrPtAIQtbWSMpI-9AQLy1VtPdWOU-WIwCm91p4UhBHH2BRVo28d7c4cu7C33beJNpi_Qew-jO2G4FswjmEleYLEleONANcQpRX2TjlHXcGTFxu9fBf7voPm349gc4JrRrjmBNec4SbVw6gKAHChkFhSQdkvxgp1Fg</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Positive-Incentive Pseudo Label Optimization for Salient Object Detection</title><source>IEEE Open Access Journals</source><source>DOAJ Directory of Open Access Journals</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Fang, Jie ; Zhang, Weitao ; Zhang, Shasha ; Wang, Nan</creator><creatorcontrib>Fang, Jie ; Zhang, Weitao ; Zhang, Shasha ; Wang, Nan</creatorcontrib><description>We present a salient object detection method in this paper. It uses a lightweight network based on multi-scale information aggregation (MIA) module and bidirectional cross-stage feature fusion (BCF2) module to speed up the reasoning process. Besides, it designs a stepwise coupling optimization strategy based on positive-incentive pseudo label to alleviate the miss detection rate for small objects and the false detection rate for big objects. It is worth noting that the positive-incentive pseudo label generation mechanism can increase the ratio of salient pixels in small objects to alleviate the severe category imbalance problem, while the stepwise coupling optimization strategy can avoid the misguidance of pseudo label to big objects. In addition, the experimental results demonstrate that our method is fairly efficient, its frame rate in reasoning phase reaches 275.6 FPS on NVIDIA RTX3080 GPU when the input resolution is set to <inline-formula> <tex-math notation="LaTeX">336\times 336 </tex-math></inline-formula>.</description><identifier>ISSN: 2169-3536</identifier><identifier>EISSN: 2169-3536</identifier><identifier>DOI: 10.1109/ACCESS.2024.3476077</identifier><identifier>CODEN: IAECCG</identifier><language>eng</language><publisher>IEEE</publisher><subject>Computational efficiency ; Computer architecture ; Convolutional neural networks ; Couplings ; Feature extraction ; high-efficiency ; lightweight network ; Object detection ; Optimization ; Performance evaluation ; positive-incentive pseudo label ; Remote sensing ; Salient object detection ; Semantics</subject><ispartof>IEEE access, 2024, Vol.12, p.153841-153850</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c261t-5f8b38d1f986dc398ee6daa7231353c106a48dac29b428b160606c99c15131b33</cites><orcidid>0009-0001-0514-1799 ; 0009-0003-9794-2917 ; 0000-0001-5601-7838 ; 0009-0002-0500-1195</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10707262$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,864,2102,4024,27633,27923,27924,27925,54933</link.rule.ids></links><search><creatorcontrib>Fang, Jie</creatorcontrib><creatorcontrib>Zhang, Weitao</creatorcontrib><creatorcontrib>Zhang, Shasha</creatorcontrib><creatorcontrib>Wang, Nan</creatorcontrib><title>Positive-Incentive Pseudo Label Optimization for Salient Object Detection</title><title>IEEE access</title><addtitle>Access</addtitle><description>We present a salient object detection method in this paper. It uses a lightweight network based on multi-scale information aggregation (MIA) module and bidirectional cross-stage feature fusion (BCF2) module to speed up the reasoning process. Besides, it designs a stepwise coupling optimization strategy based on positive-incentive pseudo label to alleviate the miss detection rate for small objects and the false detection rate for big objects. It is worth noting that the positive-incentive pseudo label generation mechanism can increase the ratio of salient pixels in small objects to alleviate the severe category imbalance problem, while the stepwise coupling optimization strategy can avoid the misguidance of pseudo label to big objects. In addition, the experimental results demonstrate that our method is fairly efficient, its frame rate in reasoning phase reaches 275.6 FPS on NVIDIA RTX3080 GPU when the input resolution is set to <inline-formula> <tex-math notation="LaTeX">336\times 336 </tex-math></inline-formula>.</description><subject>Computational efficiency</subject><subject>Computer architecture</subject><subject>Convolutional neural networks</subject><subject>Couplings</subject><subject>Feature extraction</subject><subject>high-efficiency</subject><subject>lightweight network</subject><subject>Object detection</subject><subject>Optimization</subject><subject>Performance evaluation</subject><subject>positive-incentive pseudo label</subject><subject>Remote sensing</subject><subject>Salient object detection</subject><subject>Semantics</subject><issn>2169-3536</issn><issn>2169-3536</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>RIE</sourceid><sourceid>DOA</sourceid><recordid>eNpNkNtKw0AQhhdRsNQ-gV7kBVL3lD1cllg1UGiher3sbiayJe2WJAr69G5Nkc5czDAz_8_wIXRP8JwQrB8XZbncbucUUz5nXAos5RWaUCJ0zgomri_6WzTr-x1OodKokBNUbWIfhvAFeXXwcDh12aaHzzpmK-ugzdbHIezDjx1CPGRN7LKtbUM6zNZuB37InmBIJS3v0E1j2x5m5zpF78_Lt_I1X61fqnKxyj0VZMiLRjmmatJoJWrPtAIQtbWSMpI-9AQLy1VtPdWOU-WIwCm91p4UhBHH2BRVo28d7c4cu7C33beJNpi_Qew-jO2G4FswjmEleYLEleONANcQpRX2TjlHXcGTFxu9fBf7voPm349gc4JrRrjmBNec4SbVw6gKAHChkFhSQdkvxgp1Fg</recordid><startdate>2024</startdate><enddate>2024</enddate><creator>Fang, Jie</creator><creator>Zhang, Weitao</creator><creator>Zhang, Shasha</creator><creator>Wang, Nan</creator><general>IEEE</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>DOA</scope><orcidid>https://orcid.org/0009-0001-0514-1799</orcidid><orcidid>https://orcid.org/0009-0003-9794-2917</orcidid><orcidid>https://orcid.org/0000-0001-5601-7838</orcidid><orcidid>https://orcid.org/0009-0002-0500-1195</orcidid></search><sort><creationdate>2024</creationdate><title>Positive-Incentive Pseudo Label Optimization for Salient Object Detection</title><author>Fang, Jie ; Zhang, Weitao ; Zhang, Shasha ; Wang, Nan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c261t-5f8b38d1f986dc398ee6daa7231353c106a48dac29b428b160606c99c15131b33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computational efficiency</topic><topic>Computer architecture</topic><topic>Convolutional neural networks</topic><topic>Couplings</topic><topic>Feature extraction</topic><topic>high-efficiency</topic><topic>lightweight network</topic><topic>Object detection</topic><topic>Optimization</topic><topic>Performance evaluation</topic><topic>positive-incentive pseudo label</topic><topic>Remote sensing</topic><topic>Salient object detection</topic><topic>Semantics</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Fang, Jie</creatorcontrib><creatorcontrib>Zhang, Weitao</creatorcontrib><creatorcontrib>Zhang, Shasha</creatorcontrib><creatorcontrib>Wang, Nan</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>IEEE access</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Fang, Jie</au><au>Zhang, Weitao</au><au>Zhang, Shasha</au><au>Wang, Nan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Positive-Incentive Pseudo Label Optimization for Salient Object Detection</atitle><jtitle>IEEE access</jtitle><stitle>Access</stitle><date>2024</date><risdate>2024</risdate><volume>12</volume><spage>153841</spage><epage>153850</epage><pages>153841-153850</pages><issn>2169-3536</issn><eissn>2169-3536</eissn><coden>IAECCG</coden><abstract>We present a salient object detection method in this paper. It uses a lightweight network based on multi-scale information aggregation (MIA) module and bidirectional cross-stage feature fusion (BCF2) module to speed up the reasoning process. Besides, it designs a stepwise coupling optimization strategy based on positive-incentive pseudo label to alleviate the miss detection rate for small objects and the false detection rate for big objects. It is worth noting that the positive-incentive pseudo label generation mechanism can increase the ratio of salient pixels in small objects to alleviate the severe category imbalance problem, while the stepwise coupling optimization strategy can avoid the misguidance of pseudo label to big objects. In addition, the experimental results demonstrate that our method is fairly efficient, its frame rate in reasoning phase reaches 275.6 FPS on NVIDIA RTX3080 GPU when the input resolution is set to <inline-formula> <tex-math notation="LaTeX">336\times 336 </tex-math></inline-formula>.</abstract><pub>IEEE</pub><doi>10.1109/ACCESS.2024.3476077</doi><tpages>10</tpages><orcidid>https://orcid.org/0009-0001-0514-1799</orcidid><orcidid>https://orcid.org/0009-0003-9794-2917</orcidid><orcidid>https://orcid.org/0000-0001-5601-7838</orcidid><orcidid>https://orcid.org/0009-0002-0500-1195</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2169-3536 |
| ispartof | IEEE access, 2024, Vol.12, p.153841-153850 |
| issn | 2169-3536 2169-3536 |
| language | eng |
| recordid | cdi_ieee_primary_10707262 |
| source | IEEE Open Access Journals; DOAJ Directory of Open Access Journals; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals |
| subjects | Computational efficiency Computer architecture Convolutional neural networks Couplings Feature extraction high-efficiency lightweight network Object detection Optimization Performance evaluation positive-incentive pseudo label Remote sensing Salient object detection Semantics |
| title | Positive-Incentive Pseudo Label Optimization for Salient Object Detection |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T17%3A53%3A14IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-doaj_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Positive-Incentive%20Pseudo%20Label%20Optimization%20for%20Salient%20Object%20Detection&rft.jtitle=IEEE%20access&rft.au=Fang,%20Jie&rft.date=2024&rft.volume=12&rft.spage=153841&rft.epage=153850&rft.pages=153841-153850&rft.issn=2169-3536&rft.eissn=2169-3536&rft.coden=IAECCG&rft_id=info:doi/10.1109/ACCESS.2024.3476077&rft_dat=%3Cdoaj_ieee_%3Eoai_doaj_org_article_b3087411048b4f6ebf18980cb8bb2b54%3C/doaj_ieee_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=10707262&rft_doaj_id=oai_doaj_org_article_b3087411048b4f6ebf18980cb8bb2b54&rfr_iscdi=true |