{"id":"https://openalex.org/W4402980150","doi":"https://doi.org/10.1109/icme57554.2024.10687720","title":"Correcting Pseudo Labels in Semi Supervised Object Detection with SAM","display_name":"Correcting Pseudo Labels in Semi Supervised Object Detection with SAM","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980150","doi":"https://doi.org/10.1109/icme57554.2024.10687720"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5092188956","display_name":"Pengyu Wang","orcid":"https://orcid.org/0000-0003-2805-0862"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pengyu Wang","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372739","display_name":"Jianmin Li","orcid":"https://orcid.org/0000-0002-4937-2433"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianmin Li","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101482272","display_name":"Wenbo Ding","orcid":"https://orcid.org/0000-0001-7879-7468"},"institutions":[{"id":"https://openalex.org/I4210159565","display_name":"SAIC Motor (China)","ror":"https://ror.org/051b9ta18","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210159565"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Ding","raw_affiliation_strings":["SAIC Motor Corporation Limited,SAIC AI Lab,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"SAIC Motor Corporation Limited,SAIC AI Lab,Shanghai,China","institution_ids":["https://openalex.org/I4210159565"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030955944","display_name":"Jiachen Zhong","orcid":"https://orcid.org/0000-0003-4120-7510"},"institutions":[{"id":"https://openalex.org/I4210159565","display_name":"SAIC Motor (China)","ror":"https://ror.org/051b9ta18","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210159565"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiachen Zhong","raw_affiliation_strings":["SAIC Motor Corporation Limited,SAIC AI Lab,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"SAIC Motor Corporation Limited,SAIC AI Lab,Shanghai,China","institution_ids":["https://openalex.org/I4210159565"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053946776","display_name":"Jianyong Ai","orcid":"https://orcid.org/0000-0002-9604-4328"},"institutions":[{"id":"https://openalex.org/I4210159565","display_name":"SAIC Motor (China)","ror":"https://ror.org/051b9ta18","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210159565"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyong Ai","raw_affiliation_strings":["SAIC Motor Corporation Limited,SAIC AI Lab,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"SAIC Motor Corporation Limited,SAIC AI Lab,Shanghai,China","institution_ids":["https://openalex.org/I4210159565"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5092188956"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.2632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54357141,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.8847000002861023,"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":0.8847000002861023,"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":0.8378000259399414,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.8064000010490417,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"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/computer-science","display_name":"Computer science","score":0.7664690017700195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6533792018890381},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6208232045173645},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5277419686317444},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5142719149589539},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43331021070480347}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7664690017700195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6533792018890381},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6208232045173645},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5277419686317444},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5142719149589539},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43331021070480347}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2963351448","https://openalex.org/W2964159205","https://openalex.org/W3091002423","https://openalex.org/W3172507542","https://openalex.org/W3176748778","https://openalex.org/W3178291178","https://openalex.org/W4221162144","https://openalex.org/W4312605608","https://openalex.org/W4312999279","https://openalex.org/W4313165093","https://openalex.org/W4382240273","https://openalex.org/W4386071801","https://openalex.org/W4386076058","https://openalex.org/W4386083048","https://openalex.org/W4390874575","https://openalex.org/W4391109864"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Pseudo":[0],"label":[1,34],"method":[2,8,106,120,130],"is":[3],"a":[4,77,104],"simple":[5],"and":[6,26,140],"effective":[7],"in":[9,84],"semi":[10],"supervised":[11],"object":[12],"detection(SSOD).":[13],"However,":[14],"pseudo":[15,33,43,56,82,109,138],"labels":[16,57,83,110,139],"inevitably":[17],"contain":[18],"noise,":[19],"which":[20,91],"significantly":[21],"affects":[22],"the":[23,29,39,48,65,68,112,133,136],"training":[24],"efficiency":[25],"accuracy":[27,41],"of":[28,42,67,107,135],"SSOD":[30,85,99],"model.":[31,70],"Conventional":[32],"filtering":[35],"schemes":[36],"only":[37],"consider":[38],"category":[40],"labels,":[44],"but":[45],"cannot":[46],"balance":[47],"position":[49],"quality.":[50],"The":[51],"current":[52],"methods":[53],"for":[54,80],"optimizing":[55],"also":[58],"have":[59],"drawbacks":[60],"such":[61],"as":[62],"relying":[63],"on":[64],"performance":[66],"trained":[69],"To":[71],"mitigate":[72],"this":[73],"problem,":[74],"we":[75,102],"propose":[76],"basic":[78],"process":[79],"correcting":[81],"using":[86,111],"segment":[87],"anything":[88],"model":[89,141],"(SAM),":[90],"can":[92,131],"be":[93],"simply":[94],"applied":[95],"to":[96,121],"various":[97],"existing":[98],"models.":[100],"Moreover,":[101],"optimize":[103],"specific":[105],"generating":[108],"mask":[113],"obtained":[114,137],"from":[115],"SAM.":[116],"We":[117],"apply":[118],"our":[119,129],"several":[122],"representative":[123],"models,":[124],"experiment":[125],"results":[126],"show":[127],"that":[128],"improve":[132],"quality":[134],"performance.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}