{"id":"https://openalex.org/W2890153145","doi":"https://doi.org/10.1145/3240508.3240567","title":"Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection","display_name":"Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection","publication_year":2018,"publication_date":"2018-10-15","ids":{"openalex":"https://openalex.org/W2890153145","doi":"https://doi.org/10.1145/3240508.3240567","mag":"2890153145"},"language":"en","primary_location":{"id":"doi:10.1145/3240508.3240567","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1809.05884","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yongcheng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongcheng Liu","raw_affiliation_strings":["Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lu Sheng","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lu Sheng","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jing Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Shao","raw_affiliation_strings":["SenseTime Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junjie Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Yan","raw_affiliation_strings":["SenseTime Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shiming Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiming Xiang","raw_affiliation_strings":["Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chunhong Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunhong Pan","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"700","last_page":"708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.996399998664856,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.996399998664856,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.992900013923645,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.984000027179718,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.6348999738693237},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6298999786376953},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5630000233650208},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5544999837875366},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5504000186920166},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5496000051498413},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5490999817848206},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5267000198364258}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7652999758720398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7228999733924866},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.6348999738693237},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6298999786376953},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5630000233650208},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5544999837875366},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5504000186920166},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5496000051498413},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5490999817848206},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5267000198364258},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47780001163482666},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C34872919","wikidata":"https://www.wikidata.org/wiki/Q7092302","display_name":"One-class classification","level":3,"score":0.365200012922287},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.30799999833106995},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2842000126838684},{"id":"https://openalex.org/C180462255","wikidata":"https://www.wikidata.org/wiki/Q3559736","display_name":"Standard test image","level":4,"score":0.28200000524520874},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2741999924182892},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.2718999981880188},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.26499998569488525},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.262800008058548}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3240508.3240567","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1809.05884","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.05884","pdf_url":"https://arxiv.org/pdf/1809.05884","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1809.05884","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.05884","pdf_url":"https://arxiv.org/pdf/1809.05884","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1567302070","https://openalex.org/W1908139891","https://openalex.org/W1991367009","https://openalex.org/W2007972815","https://openalex.org/W2109255472","https://openalex.org/W2117539524","https://openalex.org/W2129305389","https://openalex.org/W2146241755","https://openalex.org/W2155893237","https://openalex.org/W2408291668","https://openalex.org/W2483850719","https://openalex.org/W2592165076","https://openalex.org/W2610510511","https://openalex.org/W2765569127","https://openalex.org/W2765802795","https://openalex.org/W2787397243","https://openalex.org/W2963045696"],"related_works":[],"abstract_inverted_index":{"Multi-label":[0],"image":[1,96,122],"classification":[2,63,97,108,140,155],"is":[3,134,142,157,163],"a":[4,54,84,101],"fundamental":[5],"but":[6],"challenging":[7],"task":[8,70],"towards":[9],"general":[10],"visual":[11,47,126],"understanding.":[12],"Existing":[13],"methods":[14,29,196],"found":[15],"the":[16,45,77,107,111,116,120,124,135,139,143,151,154,161,166,174,194],"region-level":[17],"cues":[18],"(e.g.,":[19],"features":[20,127],"from":[21,67],"RoIs)":[22],"can":[23,169],"facilitate":[24],"multi-label":[25,62,95],"classification.":[26],"Nevertheless,":[27],"such":[28],"usually":[30],"require":[31],"laborious":[32],"object-level":[33,46,125],"annotations":[34],"(i.e.,":[35],"object":[36,129],"labels":[37],"and":[38,56,89,123,138,160,184,200],"bounding":[39,72],"boxes)":[40],"for":[41,119,128],"effective":[42],"learning":[43],"of":[44,153],"features.":[48],"In":[49],"this":[50,147],"paper,":[51],"we":[52,81],"propose":[53],"novel":[55],"efficient":[57],"deep":[58],"framework":[59,98,189],"to":[60,115],"boost":[61],"by":[64,100,110],"distilling":[65],"knowledge":[66,102,149],"weakly-supervised":[68,85],"detection":[69,86],"without":[71],"box":[73],"annotations.":[74],"Specifically,":[75],"given":[76],"image-level":[78],"annotations,":[79],"(1)":[80],"first":[82],"develop":[83],"(WSD)":[87],"model,":[88],"then":[90],"(2)":[91],"construct":[92],"an":[93],"end-to-end":[94],"augmented":[99],"distillation":[103],"module":[104],"that":[105,187],"guides":[106],"model":[109,113,133,137,141,156,168],"WSD":[112,132,167],"according":[114],"class-level":[117],"predictions":[118],"whole":[121],"RoIs.":[130],"The":[131],"teacher":[136],"student":[144],"model.":[145],"After":[146],"cross-task":[148],"distillation,":[150],"performance":[152,199],"significantly":[158],"improved":[159],"efficiency":[162],"maintained":[164],"since":[165],"be":[170],"safely":[171],"discarded":[172],"in":[173],"test":[175],"phase.":[176],"Extensive":[177],"experiments":[178],"on":[179,197],"two":[180],"large-scale":[181],"datasets":[182],"(MS-COCO":[183],"NUS-WIDE)":[185],"show":[186],"our":[188],"achieves":[190],"superior":[191],"performances":[192],"over":[193],"state-of-the-art":[195],"both":[198],"efficiency.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":26},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2018-09-27T00:00:00"}