{"id":"https://openalex.org/W7125908785","doi":"https://doi.org/10.1109/smc58881.2025.11343642","title":"GM-SAM: Edge-Aware Sonar Image Segmentation by Gradient-Enhanced and Multi-Perspective Fusion","display_name":"GM-SAM: Edge-Aware Sonar Image Segmentation by Gradient-Enhanced and Multi-Perspective Fusion","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125908785","doi":"https://doi.org/10.1109/smc58881.2025.11343642"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124072619","display_name":"Yue Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Liu","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089509323","display_name":"Chuantao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuantao Li","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059369286","display_name":"Z. Zhang","orcid":"https://orcid.org/0009-0005-4912-3815"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenqiang Zhang","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104306803","display_name":"Yan Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Xu","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053417873","display_name":"Jialiang Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialiang Lv","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124122267","display_name":"Chunxiao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunxiao Wang","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100538621","display_name":"Zhao Zhigang","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhigang Zhao","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83100775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7517","last_page":"7522"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.6327000260353088,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.6327000260353088,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.11479999870061874,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.0949999988079071,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sonar","display_name":"Sonar","score":0.8726000189781189},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5748000144958496},{"id":"https://openalex.org/keywords/dice","display_name":"Dice","score":0.5570999979972839},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5130000114440918},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.49570000171661377},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4796999990940094},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4625000059604645},{"id":"https://openalex.org/keywords/underwater","display_name":"Underwater","score":0.4401000142097473},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4230000078678131},{"id":"https://openalex.org/keywords/synthetic-aperture-sonar","display_name":"Synthetic aperture sonar","score":0.3961000144481659}],"concepts":[{"id":"https://openalex.org/C555745239","wikidata":"https://www.wikidata.org/wiki/Q133220","display_name":"Sonar","level":2,"score":0.8726000189781189},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.774399995803833},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7293999791145325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7075999975204468},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5748000144958496},{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.5570999979972839},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5130000114440918},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.49570000171661377},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4796999990940094},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4625000059604645},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.4401000142097473},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4230000078678131},{"id":"https://openalex.org/C181255713","wikidata":"https://www.wikidata.org/wiki/Q7662740","display_name":"Synthetic aperture sonar","level":3,"score":0.3961000144481659},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3912999927997589},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.37630000710487366},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.36550000309944153},{"id":"https://openalex.org/C2776355146","wikidata":"https://www.wikidata.org/wiki/Q357527","display_name":"Side-scan sonar","level":3,"score":0.35670000314712524},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.32600000500679016},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C137184094","wikidata":"https://www.wikidata.org/wiki/Q6764300","display_name":"Marine mammals and sonar","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.259799987077713},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C180940675","wikidata":"https://www.wikidata.org/wiki/Q7575045","display_name":"Speckle noise","level":3,"score":0.2522999942302704},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life below water","id":"https://metadata.un.org/sdg/14","score":0.7939580082893372}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W3195424217","https://openalex.org/W3204166336","https://openalex.org/W4361855172","https://openalex.org/W4388574886","https://openalex.org/W4390874575","https://openalex.org/W4390971106","https://openalex.org/W4391109864","https://openalex.org/W4391942229","https://openalex.org/W4392061582","https://openalex.org/W4394758452","https://openalex.org/W4399556757","https://openalex.org/W4401751299","https://openalex.org/W4402703114","https://openalex.org/W4402727285","https://openalex.org/W4402753647","https://openalex.org/W4402753822","https://openalex.org/W4402754280","https://openalex.org/W4404101926","https://openalex.org/W4404179005","https://openalex.org/W4404722477","https://openalex.org/W4408634392"],"related_works":[],"abstract_inverted_index":{"Sonar":[0],"imaging,":[1],"due":[2],"to":[3,6,81,105,113],"its":[4],"ability":[5],"penetrate":[7],"water":[8],"and":[9,30,57,78,87,92,143],"certain":[10],"obstacles,":[11],"has":[12],"become":[13],"a":[14,50],"pivotal":[15],"technology":[16],"in":[17,34,40],"marine":[18],"domains.":[19],"The":[20],"complexities":[21],"of":[22],"underwater":[23],"environments,":[24],"combined":[25],"with":[26,125],"the":[27,63,69,97,110,116],"low":[28],"resolution":[29],"noise":[31],"interference":[32],"inherent":[33],"sonar":[35,41],"images,":[36],"present":[37],"significant":[38],"challenges":[39],"image":[42],"segmentation.":[43],"To":[44],"address":[45],"these":[46],"issues,":[47],"we":[48],"propose":[49],"novel":[51],"approach,":[52],"GM-SAM,":[53],"which":[54],"integrates":[55,120],"denoising":[56],"multi-scale":[58],"boundary":[59],"feature":[60],"extraction":[61],"into":[62],"Segment":[64],"Anything":[65],"Model":[66],"(SAM).":[67],"Initially,":[68],"Multi-Perspective":[70],"Feature":[71],"Module":[72,100],"(MPFM)":[73],"employs":[74],"parallel":[75],"attention":[76],"mechanisms":[77],"channel-enhanced":[79],"convolutions":[80],"reduce":[82],"computational":[83],"complexity,":[84],"suppress":[85],"noise,":[86],"capture":[88],"both":[89],"local":[90],"details":[91],"global":[93],"feature.":[94],"Following":[95],"this,":[96],"Gradient-Enhanced":[98],"Transformation":[99],"(GETM)":[101],"leverages":[102],"gradient-based":[103],"operations":[104],"extract":[106],"edge":[107],"features,":[108],"enhancing":[109],"model\u2019s":[111],"sensitivity":[112],"boundaries.":[114],"Finally,":[115],"Sonar-Fusion":[117],"Adapter":[118],"module":[119],"task-specific":[121],"knowledge":[122],"from":[123,128],"MPFM":[124],"general":[126],"features":[127],"SAM.":[129],"Experimental":[130],"results":[131],"demonstrate":[132],"that":[133],"GM-SAM":[134],"significantly":[135],"outperforms":[136],"existing":[137],"methods,":[138],"achieving":[139],"superior":[140],"Dice":[141],"scores":[142],"effectively":[144],"segmenting":[145],"valid":[146],"targets.":[147]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-29T00:00:00"}