{"id":"https://openalex.org/W7140406260","doi":"https://doi.org/10.1016/j.knosys.2026.115857","title":"Plug-and-Play global and local collaborative fusion for weakly supervised object detection","display_name":"Plug-and-Play global and local collaborative fusion for weakly supervised object detection","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7140406260","doi":"https://doi.org/10.1016/j.knosys.2026.115857"},"language":"en","primary_location":{"id":"doi:10.1016/j.knosys.2026.115857","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.115857","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.knosys.2026.115857","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130642666","display_name":"Qiuyu Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuyu Liang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, 010021, Inner Mongolia, China"],"raw_orcid":"https://orcid.org/0009-0004-3261-7256","affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, 010021, Inner Mongolia, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130653409","display_name":"Yongqiang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yongqiang Zhang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, 010021, Inner Mongolia, China"],"raw_orcid":"https://orcid.org/0000-0002-0437-7337","affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, 010021, Inner Mongolia, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5130653409"],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":{"value":3130,"currency":"USD","value_usd":3130},"apc_paid":{"value":3130,"currency":"USD","value_usd":3130},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.63367822,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"342","issue":null,"first_page":"115857","last_page":"115857"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8540999889373779,"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":0.8540999889373779,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.017100000753998756,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.013000000268220901,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5720999836921692},{"id":"https://openalex.org/keywords/closeness","display_name":"Closeness","score":0.5498999953269958},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5267000198364258},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5220999717712402},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.5206000208854675},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46050000190734863},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4327000081539154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7509999871253967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7093999981880188},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5720999836921692},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.5498999953269958},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5267000198364258},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5220999717712402},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.5206000208854675},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4327000081539154},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.39730000495910645},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32420000433921814},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26510000228881836},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.knosys.2026.115857","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.115857","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.knosys.2026.115857","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.115857","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2004026774","https://openalex.org/W2031489346","https://openalex.org/W2113226722","https://openalex.org/W2117756735","https://openalex.org/W2154011501","https://openalex.org/W2156477073","https://openalex.org/W2813911573","https://openalex.org/W2906351121","https://openalex.org/W3117854388","https://openalex.org/W3126494835","https://openalex.org/W3215749523","https://openalex.org/W4200341551","https://openalex.org/W4225495512","https://openalex.org/W4285279908","https://openalex.org/W4299583570","https://openalex.org/W4323030871","https://openalex.org/W4362009341","https://openalex.org/W4376225266","https://openalex.org/W4386253300","https://openalex.org/W4391569036","https://openalex.org/W4391616610","https://openalex.org/W4393855552","https://openalex.org/W4398774772","https://openalex.org/W4401090676","https://openalex.org/W4401544324","https://openalex.org/W4403681817","https://openalex.org/W4406089761","https://openalex.org/W4406833761","https://openalex.org/W4410397428","https://openalex.org/W4411123513","https://openalex.org/W4411850053"],"related_works":[],"abstract_inverted_index":{"\u2022":[0,20,37,57],"We":[1,21,38,58,253],"propose":[2,39,208],"a":[3,23,40,100,136,163,184,192,209],"plug-and-play":[4,66,249],"global":[5,25,137,165,193],"and":[6,62,87,138,156,175,223,232,257,266,275,277],"local":[7,41,139,210],"collaborative":[8,140],"fusion":[9,43,141,212],"method":[10,67,142],"to":[11,45,50,81,84,96,123,170,187,196],"improve":[12],"the":[13,47,60,91,114,118,124,149,153,172,189,199,245],"performance":[14,281],"of":[15,64,126,152,201,247],"weakly":[16],"supervised":[17,72],"object":[18,73],"detection.":[19],"design":[22,162],"pixel-level":[24,164],"information":[26,53,112,151,166],"awareness":[27,167],"module":[28,44,169,214],"that":[29,215],"utilizes":[30],"singular":[31],"value":[32],"decomposition":[33],"for":[34,145,198,251],"image":[35,155,174,217],"reconstruction.":[36],"detail":[42,202,211],"enable":[46],"visual":[48,185],"encoder":[49,186],"learn":[51],"detailed":[52],"about":[54],"target":[55],"objects.":[56],"demonstrate":[59],"effectiveness":[61,246],"superiority":[63],"our":[65,248],"through":[68],"extensive":[69],"experiments.":[70],"Weakly":[71],"detection":[74],"(WSOD)":[75],"has":[76],"drawn":[77],"much":[78],"attention":[79],"due":[80,122],"its":[82,157],"closeness":[83],"practical":[85],"applications,":[86],"researchers":[88],"have":[89,107],"proposed":[90,144,227],"multi-instance":[92],"learning":[93,121],"(MIL)":[94],"approach":[95],"handle":[97],"it":[98],"as":[99],"multi-class":[101],"classification":[102],"problem.":[103],"Although":[104],"these":[105],"methods":[106,271],"yielded":[108],"promising":[109],"results,":[110],"extraneous":[111],"in":[113,133,204],"images":[115],"severely":[116],"affects":[117],"model\u2019s":[119],"feature":[120],"lack":[125,200],"instance-level":[127],"annotation.":[128],"To":[129],"alleviate":[130],"this":[131,134],"limitation,":[132],"paper,":[135],"is":[143],"WSOD":[146,240],"by":[147,219,272],"leveraging":[148,220],"complementary":[150],"original":[154],"low-rank":[158],"approximation.":[159],"Specifically,":[160],"we":[161,206],"(GIA)":[168],"reconstruct":[171],"input":[173,224],"remove":[176],"redundant":[177],"noise,":[178],"which":[179],"are":[180,230],"then":[181],"fed":[182],"into":[183,237],"extract":[188],"features":[190],"from":[191],"perspective.":[194],"Moreover,":[195],"compensate":[197],"preservation":[203],"GIA,":[205],"further":[207],"(LDF)":[213],"fuses":[216],"details":[218],"both":[221],"reconstructed":[222],"images.":[225],"Our":[226],"GIA-LDF":[228,250],"modules":[229],"architecture-agnostic":[231],"can":[233],"be":[234],"seamlessly":[235],"embedded":[236],"any":[238],"MIL-based":[239],"pipeline.":[241],"Extensive":[242],"experiments":[243],"validate":[244],"WSOD.":[252],"achieve":[254],"60.2%,":[255],"57.4%,":[256],"23.2%":[258],"mAP":[259],"on":[260],"PASCAL":[261],"VOC":[262,264],"2007,":[263],"2012,":[265],"COCO,":[267],"respectively,":[268],"surpassing":[269],"baseline":[270],"+2.0%,":[273],"+1.2%,":[274],"+0.3%,":[276],"establishing":[278],"new":[279],"state-of-the-art":[280],"across":[282],"all":[283],"benchmarks.":[284]},"counts_by_year":[],"updated_date":"2026-04-03T16:38:21.277918","created_date":"2026-03-27T00:00:00"}