{"id":"https://openalex.org/W4403792011","doi":"https://doi.org/10.1145/3664647.3680960","title":"WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition","display_name":"WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792011","doi":"https://doi.org/10.1145/3664647.3680960"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680960","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5013383175","display_name":"Lianghui Zhu","orcid":"https://orcid.org/0009-0005-3067-0210"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lianghui Zhu","raw_affiliation_strings":["School of EIC, Huazhong University of Science & Technology, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"School of EIC, Huazhong University of Science & Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109338351","display_name":"Jiandong Zhou","orcid":"https://orcid.org/0009-0004-8540-2400"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junwei Zhou","raw_affiliation_strings":["School of EIC, Huazhong University of Science & Technology, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"School of EIC, Huazhong University of Science & Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086921665","display_name":"Yan Liu","orcid":"https://orcid.org/0009-0005-6564-7678"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Liu","raw_affiliation_strings":["Alipay Tian Qian Security Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alipay Tian Qian Security Lab, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111979840","display_name":"Xin Hao","orcid":"https://orcid.org/0009-0008-6102-7350"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Hao","raw_affiliation_strings":["Alipay Tian Qian Security Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alipay Tian Qian Security Lab, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665053","display_name":"Wenyu Liu","orcid":"https://orcid.org/0000-0002-4582-7488"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyu Liu","raw_affiliation_strings":["School of EIC, Huazhong University of Science & Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of EIC, Huazhong University of Science & Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037191476","display_name":"Xinggang Wang","orcid":"https://orcid.org/0000-0001-6732-7823"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinggang Wang","raw_affiliation_strings":["School of EIC, Huazhong University of Science & Technology, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"School of EIC, Huazhong University of Science & Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5013383175"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":4.1597,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.95306379,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7947","last_page":"7956"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9994999766349792,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.630476713180542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5151130557060242},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4879114329814911}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.630476713180542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5151130557060242},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4879114329814911}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680960","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2168804568","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2441255125","https://openalex.org/W2552414813","https://openalex.org/W2559348937","https://openalex.org/W2604260814","https://openalex.org/W2606831796","https://openalex.org/W2798269247","https://openalex.org/W2798748179","https://openalex.org/W2813911573","https://openalex.org/W2894666165","https://openalex.org/W2895236117","https://openalex.org/W2954087924","https://openalex.org/W2955278847","https://openalex.org/W2962867364","https://openalex.org/W2963254348","https://openalex.org/W2963311325","https://openalex.org/W2963603913","https://openalex.org/W2963949812","https://openalex.org/W2963952323","https://openalex.org/W2991533779","https://openalex.org/W2991662170","https://openalex.org/W2994041372","https://openalex.org/W3034329658","https://openalex.org/W3035725370","https://openalex.org/W3085685449","https://openalex.org/W3095191037","https://openalex.org/W3107653507","https://openalex.org/W3109073404","https://openalex.org/W3119344692","https://openalex.org/W3169200952","https://openalex.org/W3175385356","https://openalex.org/W3175704361","https://openalex.org/W3176692018","https://openalex.org/W3180169285","https://openalex.org/W3204507850","https://openalex.org/W3207624121","https://openalex.org/W3207676276","https://openalex.org/W3207731638","https://openalex.org/W3207782762","https://openalex.org/W3213276254","https://openalex.org/W4304014881","https://openalex.org/W4304091783","https://openalex.org/W4307795760","https://openalex.org/W4312105387","https://openalex.org/W4312324516","https://openalex.org/W4312578467","https://openalex.org/W4312748662","https://openalex.org/W4312792327","https://openalex.org/W4312815172","https://openalex.org/W4312866875","https://openalex.org/W4386057743","https://openalex.org/W4390871862","https://openalex.org/W4390872613","https://openalex.org/W4390874156","https://openalex.org/W4393156560"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Weakly-supervised":[0],"visual":[1],"recognition":[2],"using":[3],"inexact":[4],"supervision":[5],"is":[6],"a":[7,48],"critical":[8,61],"yet":[9],"challenging":[10],"learning":[11,24],"problem.":[12],"It":[13,88],"significantly":[14,111],"reduces":[15],"human":[16,96],"labeling":[17],"costs":[18],"and":[19,25,31,38,73,81,98,104,118,129],"traditionally":[20],"relies":[21],"on":[22],"multi-instance":[23],"pseudo-labeling.":[26],"This":[27],"paper":[28],"introduces":[29],"WeakSAM":[30,58,110],"solves":[32],"the":[33,42,53,91],"weakly-supervised":[34],"object":[35,102],"detection":[36,103],"(WSOD)":[37],"segmentation":[39],"by":[40],"utilizing":[41],"pre-learned":[43],"world":[44],"knowledge":[45],"contained":[46],"in":[47,63,101,116],"vision":[49],"foundation":[50],"model,":[51],"i.e.,":[52,67],"Segment":[54],"Anything":[55],"Model":[56],"(SAM).":[57],"addresses":[59,90],"two":[60],"limitations":[62],"traditional":[64],"WSOD":[65,117],"retraining,":[66],"pseudo":[68],"ground":[69],"truth":[70],"(PGT)":[71],"incompleteness":[72],"noisy":[74],"PGT":[75,79],"instances,":[76],"through":[77],"adaptive":[78],"generation":[80],"Region":[82],"of":[83,94,127],"Interest":[84],"(RoI)":[85],"drop":[86],"regularization.":[87],"also":[89],"SAM's":[92],"shortcomings":[93],"requiring":[95],"prompts":[97],"category":[99],"unawareness":[100],"segmentation.":[105],"Our":[106],"results":[107],"indicate":[108],"that":[109],"surpasses":[112],"previous":[113],"state-of-the-art":[114],"methods":[115],"WSIS":[119],"benchmarks":[120],"with":[121],"large":[122],"margins,":[123],"i.e.":[124],"average":[125],"improvements":[126],"7.4%":[128],"8.5%,":[130],"respectively.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}