{"id":"https://openalex.org/W4304086143","doi":"https://doi.org/10.1145/3503161.3548242","title":"Mixed Supervision for Instance Learning in Object Detection with Few-shot Annotation","display_name":"Mixed Supervision for Instance Learning in Object Detection with Few-shot Annotation","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304086143","doi":"https://doi.org/10.1145/3503161.3548242"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548242","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th 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/A5100667724","display_name":"Yi Zhong","orcid":"https://orcid.org/0000-0002-9309-3407"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Zhong","raw_affiliation_strings":["Sun Yat-Sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103090275","display_name":"Chengyao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyao Wang","raw_affiliation_strings":["Sun Yat-Sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100780833","display_name":"Shiyong Li","orcid":"https://orcid.org/0000-0002-2990-0497"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyong Li","raw_affiliation_strings":["AI Application Research Center, Huawei, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"AI Application Research Center, Huawei, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100940923","display_name":"Zhou Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu Zhou","raw_affiliation_strings":["AI Application Research Center, Huawei, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"AI Application Research Center, Huawei, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100631216","display_name":"Yaowei Wang","orcid":"https://orcid.org/0000-0003-2197-9038"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaowei Wang","raw_affiliation_strings":["Pengcheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108050904","display_name":"Wei\u2010Shi Zheng","orcid":"https://orcid.org/0000-0001-8327-0003"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Shi Zheng","raw_affiliation_strings":["Sun Yat-Sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100667724"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.06,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.27841152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"648","last_page":"658"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9984999895095825,"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":0.9955000281333923,"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/computer-science","display_name":"Computer science","score":0.8273307085037231},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6008902788162231},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5524371266365051},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5519530177116394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5426571369171143},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.5385014414787292},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5154410600662231},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4862569570541382},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47779354453086853},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.27539190649986267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8273307085037231},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6008902788162231},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5524371266365051},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5519530177116394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5426571369171143},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.5385014414787292},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5154410600662231},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4862569570541382},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47779354453086853},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27539190649986267},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548242","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":28,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W1991367009","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2133324800","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2248800885","https://openalex.org/W2519284461","https://openalex.org/W2604260814","https://openalex.org/W2610510511","https://openalex.org/W2618530766","https://openalex.org/W2813911573","https://openalex.org/W2903049906","https://openalex.org/W2962685835","https://openalex.org/W2963351448","https://openalex.org/W2963516811","https://openalex.org/W2963603913","https://openalex.org/W2963952323","https://openalex.org/W2966746892","https://openalex.org/W2981842371","https://openalex.org/W2991662170","https://openalex.org/W3017351200","https://openalex.org/W3035725370","https://openalex.org/W3106250896","https://openalex.org/W3108828338","https://openalex.org/W3133929212"],"related_works":["https://openalex.org/W4376620596","https://openalex.org/W3177249605","https://openalex.org/W2534152068","https://openalex.org/W3138508047","https://openalex.org/W1972515067","https://openalex.org/W1689909837","https://openalex.org/W4293054914","https://openalex.org/W4298525700","https://openalex.org/W2953362004","https://openalex.org/W2549121492"],"abstract_inverted_index":{"Mixed":[0],"supervision":[1,39,55],"for":[2,27,88,169],"object":[3],"detection":[4],"(MSOD)":[5],"that":[6,43,213],"utilizes":[7],"image-level":[8,46],"annotations":[9,16,34,70,83,124,166],"and":[10,35,75,98,199,207,233],"a":[11,28,60,66,177,182,225],"small":[12],"amount":[13,30],"of":[14,31,68,201],"instance-level":[15,33,69,82,123,165],"has":[17],"emerged":[18],"as":[19,59],"an":[20,157],"efficient":[21],"tool":[22],"by":[23,125,162,195],"alleviating":[24],"the":[25,53,112,131,137,141,154,163,192,197,205,214,230,234],"requirement":[26],"large":[29,226],"costly":[32],"providing":[36],"effective":[37,96],"instance":[38,56,158,185],"on":[40,85,136,228],"previous":[41],"methods":[42],"only":[44],"use":[45],"annotations.":[47,106],"In":[48,107],"this":[49],"work,":[50],"we":[51,90,109],"introduce":[52],"mixed":[54,155,221],"learning":[57],"(MSIL),":[58],"novel":[61],"MSOD":[62],"framework":[63,217],"to":[64,71,92,118,129,134,148,190],"leverage":[65],"handful":[67],"provide":[72,119],"more":[73,95,150,171,178],"explicit":[74,97,120],"implicit":[76,99,151],"supervision.":[77],"Rather":[78],"than":[79],"just":[80],"adding":[81],"directly":[84],"loss":[86],"functions":[87],"detection,":[89],"aim":[91],"dig":[93],"out":[94],"relations":[100],"between":[101,153],"these":[102],"two":[103],"different":[104],"level":[105],"particular,":[108],"firstly":[110],"propose":[111],"Instance-Annotation":[113],"Guided":[114],"Image":[115],"Classification":[116],"strategy":[117,160,187],"guidance":[121],"from":[122],"using":[126],"positional":[127],"relation":[128],"force":[130],"image":[132],"classifier":[133],"focus":[135],"proposals":[138],"which":[139],"contain":[140],"correct":[142],"object.":[143],"And":[144],"then,":[145],"in":[146],"order":[147],"exploit":[149],"interaction":[152],"annotations,":[156],"reproduction":[159],"guided":[161],"extra":[164],"is":[167,188],"developed":[168],"generating":[170],"accurate":[172],"pseudo":[173],"ground":[174],"truth,":[175],"achieving":[176],"discriminative":[179],"detector.":[180],"Finally,":[181],"false":[183],"target":[184],"mining":[186],"used":[189],"refine":[191],"above":[193],"processing":[194],"enriching":[196],"number":[198],"diversity":[200],"training":[202],"instances":[203],"with":[204,224],"position":[206],"score":[208],"information.":[209],"Our":[210],"experiments":[211],"show":[212],"proposed":[215],"MSIL":[216],"outperforms":[218],"recent":[219],"state-of-the-art":[220],"supervised":[222],"detectors":[223],"margin":[227],"both":[229],"Pascal":[231],"VOC2007":[232],"MS-COCO":[235],"dataset.":[236]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}