{"id":"https://openalex.org/W4411687348","doi":"https://doi.org/10.1109/tip.2025.3581729","title":"WS-SAM: Generalizing SAM to Weakly Supervised Object Detection With Category Label","display_name":"WS-SAM: Generalizing SAM to Weakly Supervised Object Detection With Category Label","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411687348","doi":"https://doi.org/10.1109/tip.2025.3581729","pmid":"https://pubmed.ncbi.nlm.nih.gov/40569798"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3581729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3581729","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100649232","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0002-6956-7342"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["College of Information Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-6956-7342","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065669986","display_name":"Tong Jia","orcid":"https://orcid.org/0000-0003-1424-798X"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Jia","raw_affiliation_strings":["College of Information Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0003-1424-798X","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658200","display_name":"Qilong Wang","orcid":"https://orcid.org/0000-0002-3765-9787"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qilong Wang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-3765-9787","affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100636655","display_name":"Wangmeng Zuo","orcid":"https://orcid.org/0000-0002-3330-783X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangmeng Zuo","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-3330-783X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71494884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"34","issue":null,"first_page":"4052","last_page":"4066"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9948999881744385,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9948999881744385,"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":0.9860000014305115,"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/T10057","display_name":"Face and Expression Recognition","score":0.9843999743461609,"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/object","display_name":"Object (grammar)","score":0.6064866185188293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6034061312675476},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5984084606170654},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5922884941101074},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5389145016670227},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4578089416027069},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.418979674577713},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37802308797836304}],"concepts":[{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6064866185188293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6034061312675476},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5984084606170654},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5922884941101074},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5389145016670227},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4578089416027069},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.418979674577713},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37802308797836304}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2025.3581729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3581729","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:40569798","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40569798","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G1527161518","display_name":null,"funder_award_id":"62206043","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1730356339","display_name":null,"funder_award_id":"2023M730517","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G359844450","display_name":null,"funder_award_id":"2024T170114","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G3638665456","display_name":null,"funder_award_id":"62206043, 62276186 and U22A2063","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3954896424","display_name":null,"funder_award_id":"2023M730517 and 2024T170114","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G4966548598","display_name":null,"funder_award_id":"U22A2063","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5478172478","display_name":null,"funder_award_id":"62276186","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1991367009","https://openalex.org/W2037227137","https://openalex.org/W2088049833","https://openalex.org/W2168356304","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2412782625","https://openalex.org/W2601564443","https://openalex.org/W2604260814","https://openalex.org/W2813911573","https://openalex.org/W2962858109","https://openalex.org/W2962914239","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963516811","https://openalex.org/W2963603913","https://openalex.org/W2963952323","https://openalex.org/W2982770724","https://openalex.org/W2986357608","https://openalex.org/W2991533779","https://openalex.org/W2991662170","https://openalex.org/W3017351200","https://openalex.org/W3034329658","https://openalex.org/W3035725370","https://openalex.org/W3047237378","https://openalex.org/W3096609285","https://openalex.org/W3126494835","https://openalex.org/W3142837074","https://openalex.org/W3173331776","https://openalex.org/W3176692018","https://openalex.org/W3190805089","https://openalex.org/W3214910576","https://openalex.org/W4221079664","https://openalex.org/W4221167637","https://openalex.org/W4307795760","https://openalex.org/W4312748662","https://openalex.org/W4312750973","https://openalex.org/W4312792327","https://openalex.org/W4313175608","https://openalex.org/W4313291231","https://openalex.org/W4382788129","https://openalex.org/W4385764436","https://openalex.org/W4386057743","https://openalex.org/W4386790226","https://openalex.org/W4387694723","https://openalex.org/W4389890901","https://openalex.org/W4390190100","https://openalex.org/W4390871862","https://openalex.org/W4390872875","https://openalex.org/W4390874291","https://openalex.org/W4390874575","https://openalex.org/W4391454573","https://openalex.org/W4393147872","https://openalex.org/W4398757498","https://openalex.org/W4401878746","https://openalex.org/W4402727450","https://openalex.org/W4402727612","https://openalex.org/W4402916242","https://openalex.org/W4402952511","https://openalex.org/W4403021086","https://openalex.org/W4403792011","https://openalex.org/W4405102034","https://openalex.org/W4406753732","https://openalex.org/W6620707391","https://openalex.org/W6783940252","https://openalex.org/W6784930956","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6838393215","https://openalex.org/W6838701581","https://openalex.org/W6851134139","https://openalex.org/W6852404605","https://openalex.org/W6870839691","https://openalex.org/W6873072034","https://openalex.org/W6875659071"],"related_works":["https://openalex.org/W2114275278","https://openalex.org/W4292830139","https://openalex.org/W4319309705","https://openalex.org/W1489511283","https://openalex.org/W2974914859","https://openalex.org/W2026565050","https://openalex.org/W2110244802","https://openalex.org/W2163728705","https://openalex.org/W949345935","https://openalex.org/W2109550041"],"abstract_inverted_index":{"Building":[0],"an":[1,211],"effective":[2],"object":[3,131,148,203],"detector":[4],"usually":[5],"depends":[6],"on":[7,66,145,261,318],"large":[8],"well-annotated":[9],"training":[10],"samples.":[11],"While":[12],"annotating":[13],"such":[14,125,161],"dataset":[15],"is":[16,33,171,299],"extremely":[17],"laborious":[18,54],"and":[19,30,49,57,98,112,160,167,176,222,274,293,325,328],"costly,":[20],"where":[21,253],"box-level":[22,38],"supervision":[23],"which":[24,194],"contains":[25],"both":[26],"accurate":[27],"classification":[28,263],"category":[29,173,181,206],"localization":[31],"coordinate":[32],"required.":[34],"Compared":[35],"to":[36,62,108,123,128,134,183,200,215,248,302],"above":[37,189],"supervised":[39,43,75,79,130,139,147,202],"annotation,":[40],"those":[41],"weakly":[42,78,129,146,201],"learning":[44],"manners":[45],"(e.g,,":[46],"category,":[47],"point":[48],"scribble)":[50],"need":[51],"relatively":[52],"less":[53],"annotation":[55],"cost,":[56],"provide":[58],"a":[59,94,172,231,269,281,296],"feasible":[60],"way":[61],"mitigate":[63],"the":[64,67,71,119,136,180,184,220,226,236,241,245,250,254,262,276,288,304,313,329],"reliance":[65],"dataset.":[68],"Because":[69],"of":[70,73,118,219,238,315],"lack":[72],"sufficient":[74],"information,":[76],"current":[77],"methods":[80],"cannot":[81,178],"achieve":[82,338],"satisfactory":[83],"detection":[84,132,149,204,320],"performance.":[85],"Recently,":[86],"Segment":[87,196],"Anything":[88,197],"Model":[89,198],"(SAM)":[90,199],"has":[91],"appeared":[92],"as":[93,244,280],"task-agnostic":[95],"foundation":[96],"model":[97],"shown":[99],"promising":[100],"performance":[101],"improvement":[102,340],"in":[103,138,230],"many":[104],"related":[105],"works":[106],"due":[107],"its":[109],"powerful":[110],"generalization":[111],"data":[113],"processing":[114],"abilities.":[115],"The":[116],"properties":[117],"SAM":[120,144,156,170,239],"inspire":[121],"us":[122],"adopt":[124],"basic":[126],"benchmark":[127],"field":[133],"compensate":[135],"deficiencies":[137],"information.":[140,310],"However,":[141],"directly":[142],"deploying":[143],"task":[150],"meets":[151],"with":[152,205],"two":[153],"issues.":[154],"Firstly,":[155],"needs":[157],"meticulously-designed":[158],"prompts,":[159],"expert-level":[162],"prompts":[163,255],"restrict":[164],"their":[165],"applicability":[166],"practicality.":[168],"Besides,":[169],"unawareness":[174],"model,":[175],"it":[177],"assign":[179],"labels":[182],"generated":[185,259],"predictions.":[186],"To":[187],"solve":[188],"issues,":[190],"we":[191,209],"propose":[192],"WS-SAM,":[193],"generalizes":[195],"label.":[207],"Specifically,":[208],"design":[210],"adaptive":[212],"prompt":[213,246],"generator":[214],"take":[216],"full":[217],"advantages":[218],"spatial":[221],"semantic":[223],"information":[224],"from":[225,240],"prompt.":[227],"It":[228],"employs":[229],"self-prompting":[232],"manner":[233],"by":[234,286,307],"taking":[235],"output":[237],"previous":[242],"iteration":[243],"input":[247],"guide":[249],"next":[251],"iteration,":[252],"can":[256,337],"be":[257],"adaptively":[258],"based":[260],"activation":[264],"map.":[265],"We":[266,311],"also":[267,300],"develop":[268],"segmentation":[270],"mask":[271],"refinement":[272],"module":[273],"formulate":[275],"label":[277],"assignment":[278],"process":[279],"shortest":[282],"path":[283],"optimization":[284],"problem":[285],"considering":[287],"similarity":[289],"between":[290],"each":[291],"location":[292],"prompts.":[294],"Furthermore,":[295],"bidirectional":[297],"adapter":[298],"implemented":[301],"resolve":[303],"domain":[305],"discrepancy":[306],"incorporating":[308],"domain-specific":[309],"evaluate":[312],"effectiveness":[314],"our":[316,334],"method":[317,336],"several":[319],"datasets":[321],"(e.g.,":[322],"PASCAL":[323],"VOC":[324],"MS":[326],"COCO),":[327],"experiment":[330],"results":[331],"show":[332],"that":[333],"proposed":[335],"clear":[339],"over":[341],"state-of-the-art":[342],"methods,":[343],"while":[344],"performing":[345],"favorably":[346],"against":[347],"state-of-the-arts.":[348]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}