{"id":"https://openalex.org/W7204199808","doi":"https://doi.org/10.3390/app16178470","title":"Weakly Supervised Segmentation of Macroalgae Through Gradient Analysis in Convolutional Neural Networks and Segment Anything Model","display_name":"Weakly Supervised Segmentation of Macroalgae Through Gradient Analysis in Convolutional Neural Networks and Segment Anything Model","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204199808","doi":"https://doi.org/10.3390/app16178470"},"language":"en","primary_location":{"id":"doi:10.3390/app16178470","doi":"https://doi.org/10.3390/app16178470","is_oa":true,"landing_page_url":"https://doi.org/10.3390/app16178470","pdf_url":null,"source":{"id":"https://openalex.org/S4210205812","display_name":"Applied Sciences","issn_l":"2076-3417","issn":["2076-3417"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Sciences","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/app16178470","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128695661","display_name":"\u00c1urea Genoveva Carballo P\u00e9rez","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I6289922","display_name":"Universidade de Vigo","ror":"https://ror.org/05rdf8595","country_code":"ES","type":"education","lineage":["https://openalex.org/I6289922"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"\u00c1urea Genoveva Carballo P\u00e9rez","raw_affiliation_strings":["atlanTTic, Aerospace Technologies Research Group, Universidade de Vigo, 36310 Vigo, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"atlanTTic, Aerospace Technologies Research Group, Universidade de Vigo, 36310 Vigo, Spain","institution_ids":["https://openalex.org/I6289922"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120197812","display_name":"Pablo Magari\u00f1os-Docampo","orcid":"https://orcid.org/0009-0002-9817-0368","observed_orcids":["https://orcid.org/0009-0002-9817-0368"]},"institutions":[{"id":"https://openalex.org/I6289922","display_name":"Universidade de Vigo","ror":"https://ror.org/05rdf8595","country_code":"ES","type":"education","lineage":["https://openalex.org/I6289922"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pablo Magari\u00f1os-Docampo","raw_affiliation_strings":["atlanTTic, Aerospace Technologies Research Group, Universidade de Vigo, 36310 Vigo, Spain"],"raw_orcid":"https://orcid.org/0009-0002-9817-0368","affiliations":[{"raw_affiliation_string":"atlanTTic, Aerospace Technologies Research Group, Universidade de Vigo, 36310 Vigo, Spain","institution_ids":["https://openalex.org/I6289922"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061555555","display_name":"Pedro Orgeira-Crespo","orcid":"https://orcid.org/0000-0003-2734-4586","observed_orcids":["https://orcid.org/0000-0003-2734-4586"]},"institutions":[{"id":"https://openalex.org/I6289922","display_name":"Universidade de Vigo","ror":"https://ror.org/05rdf8595","country_code":"ES","type":"education","lineage":["https://openalex.org/I6289922"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Pedro Orgeira-Crespo","raw_affiliation_strings":["Department of Mechanical Engineering, Heat Engines and Machines and Fluids, Aerospace Engineering School, University of Vigo, Campus Orense, 32004 Orense, Spain","atlanTTic, Aerospace Technologies Research Group, Universidade de Vigo, 36310 Vigo, Spain"],"raw_orcid":"https://orcid.org/0000-0003-2734-4586","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Heat Engines and Machines and Fluids, Aerospace Engineering School, University of Vigo, Campus Orense, 32004 Orense, Spain","institution_ids":["https://openalex.org/I6289922"]},{"raw_affiliation_string":"atlanTTic, Aerospace Technologies Research Group, Universidade de Vigo, 36310 Vigo, Spain","institution_ids":["https://openalex.org/I6289922"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053357771","display_name":"Fernando Aguado Agelet","orcid":"https://orcid.org/0000-0003-2713-1943","observed_orcids":["https://orcid.org/0000-0003-2713-1943"]},"institutions":[{"id":"https://openalex.org/I6289922","display_name":"Universidade de Vigo","ror":"https://ror.org/05rdf8595","country_code":"ES","type":"education","lineage":["https://openalex.org/I6289922"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Fernando Aguado-Agelet","raw_affiliation_strings":["Telecommunication Engineering School, University of Vigo, 36310 Vigo, Spain","atlanTTic, Aerospace Technologies Research Group, Universidade de Vigo, 36310 Vigo, Spain"],"raw_orcid":"https://orcid.org/0000-0003-2713-1943","affiliations":[{"raw_affiliation_string":"Telecommunication Engineering School, University of Vigo, 36310 Vigo, Spain","institution_ids":["https://openalex.org/I6289922"]},{"raw_affiliation_string":"atlanTTic, Aerospace Technologies Research Group, Universidade de Vigo, 36310 Vigo, Spain","institution_ids":["https://openalex.org/I6289922"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5061555555"],"corresponding_institution_ids":["https://openalex.org/I6289922"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2896},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2896},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67559427,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"17","first_page":"8470","last_page":"8470"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8848000168800354,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8848000168800354,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.03720000013709068,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.01899999938905239,"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/weakly-supervised-segmentation","display_name":"weakly supervised segmentation","score":0.9490000009536743},{"id":"https://openalex.org/keywords/gradient-analysis","display_name":"gradient analysis","score":0.7649999856948853},{"id":"https://openalex.org/keywords/segment-anything-model-2","display_name":"Segment Anything Model 2","score":0.75},{"id":"https://openalex.org/keywords/seaweed","display_name":"seaweed","score":0.5490000247955322},{"id":"https://openalex.org/keywords/fucus","display_name":"Fucus","score":0.925000011920929},{"id":"https://openalex.org/keywords/laminaria","display_name":"Laminaria","score":1.0},{"id":"https://openalex.org/keywords/ulva","display_name":"Ulva","score":0.9980000257492065},{"id":"https://openalex.org/keywords/optical-imagery","display_name":"optical imagery","score":0.640999972820282}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7674999833106995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7493000030517578},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.7347000241279602},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7125999927520752},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6840000152587891},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6320000290870667},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5151000022888184},{"id":"https://openalex.org/C163892561","wikidata":"https://www.wikidata.org/wiki/Q2613728","display_name":"S\u00f8rensen\u2013Dice coefficient","level":4,"score":0.5051000118255615},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.43779999017715454},{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.31700000166893005},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2522999942302704}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/app16178470","doi":"https://doi.org/10.3390/app16178470","is_oa":true,"landing_page_url":"https://doi.org/10.3390/app16178470","pdf_url":null,"source":{"id":"https://openalex.org/S4210205812","display_name":"Applied Sciences","issn_l":"2076-3417","issn":["2076-3417"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Sciences","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0177906facaf46a9b597cbcc3556c964","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/0177906facaf46a9b597cbcc3556c964","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Applied Sciences, Vol 16, Iss 17, p 8470 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/app16178470","doi":"https://doi.org/10.3390/app16178470","is_oa":true,"landing_page_url":"https://doi.org/10.3390/app16178470","pdf_url":null,"source":{"id":"https://openalex.org/S4210205812","display_name":"Applied Sciences","issn_l":"2076-3417","issn":["2076-3417"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Sciences","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.8765207529067993,"display_name":"Life below water","id":"https://metadata.un.org/sdg/14"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2295107390","https://openalex.org/W2610018085","https://openalex.org/W2616247523","https://openalex.org/W2765793020","https://openalex.org/W3035253074","https://openalex.org/W3035712793","https://openalex.org/W3115878113","https://openalex.org/W3176482836","https://openalex.org/W3194719203","https://openalex.org/W4220881159","https://openalex.org/W4229494842","https://openalex.org/W4312154915","https://openalex.org/W4390874575","https://openalex.org/W4394625830","https://openalex.org/W4401475400","https://openalex.org/W4402660125","https://openalex.org/W4402752105","https://openalex.org/W4402753685","https://openalex.org/W4403241880","https://openalex.org/W4406695796","https://openalex.org/W4407566400","https://openalex.org/W4412954933","https://openalex.org/W4416413050","https://openalex.org/W7171530645"],"related_works":[],"abstract_inverted_index":{"Segmenting":[0],"marine":[1],"macroalgae":[2,58],"from":[3,28,48],"optical":[4],"imagery":[5],"typically":[6],"requires":[7],"pixel-level":[8],"annotations":[9],"that":[10,24,119],"are":[11],"costly":[12],"and":[13,62,88,95,113,134,179],"hard":[14],"to":[15,74,79],"scale.":[16],"This":[17],"work":[18],"proposes":[19],"a":[20,44,167],"weakly":[21],"supervised":[22],"pipeline":[23,165],"derives":[25],"segmentation":[26],"masks":[27],"image-level":[29],"classification":[30],"labels":[31],"alone,":[32],"eliminating":[33],"manual":[34],"spatial":[35,81],"annotations.":[36],"The":[37,139],"method":[38],"has":[39],"three":[40,57],"stages:":[41],"(1)":[42],"training":[43,149],"six-layer":[45],"convolutional":[46,77],"classifier":[47,140],"scratch,":[49],"without":[50],"weight":[51],"transfer,":[52],"on":[53,150],"1818":[54],"images":[55,158],"of":[56,68,83,131,148,170,174,177,181,185],"genera":[59],"(Fucus,":[60],"Laminaria,":[61],"Ulva);":[63],"(2)":[64],"analyzing":[65],"the":[66,69,84,120,129,163,186,191],"gradients":[67],"classifier\u2019s":[70],"output":[71],"with":[72,144],"respect":[73],"all":[75],"intermediate":[76],"layers":[78,133],"build":[80],"heatmaps":[82],"most":[85],"decision-relevant":[86],"regions;":[87],"(3)":[89],"extracting":[90],"keypoints":[91,188],"via":[92],"non-maximum":[93],"suppression":[94],"using":[96],"them":[97],"as":[98],"prompts":[99],"for":[100,161],"Segment":[101],"Anything":[102],"Model":[103],"2":[104],"(SAM2).":[105],"We":[106],"compare":[107],"two":[108],"importance":[109,123],"metrics\u2014sensitivity":[110],"(gradient":[111,115],"only)":[112],"contribution":[114],"times":[116],"activation)\u2014and":[117],"show":[118],"former":[121],"distributes":[122],"more":[124,136],"evenly":[125],"across":[126],"layers,":[127],"preserving":[128],"resolution":[130],"early":[132],"yielding":[135],"precise":[137],"localizations.":[138],"reaches":[141],"94.5%":[142],"accuracy":[143],"under":[145],"15":[146],"min":[147],"conventional":[151],"hardware.":[152],"On":[153],"42":[154],"manually":[155],"annotated":[156,192],"validation":[157],"used":[159],"exclusively":[160],"evaluation,":[162],"complete":[164],"achieves":[166],"mean":[168],"IoU":[169],"0.44,":[171],"Dice":[172],"coefficient":[173],"0.51,":[175],"precision":[176],"0.70,":[178],"recall":[180],"0.54,":[182],"while":[183],"80%":[184],"extracted":[187],"fall":[189],"inside":[190],"algae.":[193]},"counts_by_year":[],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2026-08-26T00:00:00"}