{"id":"https://openalex.org/W3208365968","doi":"https://doi.org/10.1109/iv48863.2021.9575963","title":"Boosting Supervised Learning Performance with Co-training","display_name":"Boosting Supervised Learning Performance with Co-training","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3208365968","doi":"https://doi.org/10.1109/iv48863.2021.9575963","mag":"3208365968"},"language":"en","primary_location":{"id":"doi:10.1109/iv48863.2021.9575963","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv48863.2021.9575963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.09797","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021263036","display_name":"Xinnan Du","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xinnan Du","raw_affiliation_strings":["Carnegie Mellon University,NVIDIA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,NVIDIA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101962788","display_name":"William Zhang","orcid":"https://orcid.org/0009-0000-8189-6782"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Zhang","raw_affiliation_strings":["NVIDIA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101540588","display_name":"Jos\u00e9 M. Alvarez","orcid":"https://orcid.org/0000-0002-7535-6322"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jose M. Alvarez","raw_affiliation_strings":["NVIDIA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021263036"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57012412,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"28","issue":null,"first_page":"540","last_page":"545"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9957000017166138,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9944000244140625,"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":0.816543698310852},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.7219542264938354},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7069864273071289},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6943077445030212},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6922571063041687},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.5861111283302307},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5795742273330688},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5777882933616638},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5433131456375122},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.48789259791374207},{"id":"https://openalex.org/keywords/co-training","display_name":"Co-training","score":0.4557151794433594},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4393559396266937},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3670509457588196},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2131437361240387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.816543698310852},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.7219542264938354},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7069864273071289},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6943077445030212},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6922571063041687},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.5861111283302307},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5795742273330688},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5777882933616638},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5433131456375122},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.48789259791374207},{"id":"https://openalex.org/C2776959682","wikidata":"https://www.wikidata.org/wiki/Q17005296","display_name":"Co-training","level":3,"score":0.4557151794433594},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4393559396266937},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3670509457588196},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2131437361240387},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iv48863.2021.9575963","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv48863.2021.9575963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2111.09797","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.09797","pdf_url":"https://arxiv.org/pdf/2111.09797","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:2111.09797","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.09797","pdf_url":"https://arxiv.org/pdf/2111.09797","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":44,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W582055897","https://openalex.org/W1542791059","https://openalex.org/W2025768430","https://openalex.org/W2144796873","https://openalex.org/W2173520492","https://openalex.org/W2321533354","https://openalex.org/W2326925005","https://openalex.org/W2412320034","https://openalex.org/W2432541215","https://openalex.org/W2549401308","https://openalex.org/W2558661413","https://openalex.org/W2768591600","https://openalex.org/W2785325870","https://openalex.org/W2890538051","https://openalex.org/W2913340405","https://openalex.org/W2950673314","https://openalex.org/W2958360136","https://openalex.org/W2962824366","https://openalex.org/W2963420272","https://openalex.org/W2963684088","https://openalex.org/W2963722008","https://openalex.org/W2963877604","https://openalex.org/W2964056935","https://openalex.org/W2965994363","https://openalex.org/W2968879723","https://openalex.org/W2981801509","https://openalex.org/W2999219213","https://openalex.org/W3005680577","https://openalex.org/W3034781633","https://openalex.org/W3034978746","https://openalex.org/W3035004134","https://openalex.org/W3094454579","https://openalex.org/W4294568686","https://openalex.org/W4295112452","https://openalex.org/W6616954417","https://openalex.org/W6685352114","https://openalex.org/W6700872662","https://openalex.org/W6715501732","https://openalex.org/W6715861406","https://openalex.org/W6718046261","https://openalex.org/W6754005058","https://openalex.org/W6774314701","https://openalex.org/W6784660784"],"related_works":["https://openalex.org/W2133556223","https://openalex.org/W1520691178","https://openalex.org/W2186473728","https://openalex.org/W4312414840","https://openalex.org/W192740413","https://openalex.org/W2131153761","https://openalex.org/W2891078859","https://openalex.org/W60792937","https://openalex.org/W2913865199","https://openalex.org/W2059598258"],"abstract_inverted_index":{"Deep":[0],"learning":[1,59,65],"perception":[2,129],"models":[3],"require":[4],"a":[5,32,55,75,84],"massive":[6],"amount":[7],"of":[8,25,114,142],"labeled":[9],"training":[10,108],"data":[11,18],"to":[12,21,46,96,106],"achieve":[13],"good":[14],"performance.":[15],"While":[16],"unlabeled":[17,48,160],"is":[19,27],"easy":[20],"acquire,":[22],"the":[23,112,140,143,148],"cost":[24],"labeling":[26],"prohibitive":[28],"and":[29,77,100,103,124],"could":[30,62],"create":[31],"tremendous":[33],"burden":[34],"on":[35,127],"companies":[36],"or":[37],"individuals.":[38],"Recently,":[39],"self-supervision":[40],"has":[41],"emerged":[42],"as":[43],"an":[44],"alternative":[45],"leveraging":[47],"data.":[49,161],"In":[50],"this":[51],"paper,":[52],"we":[53,73],"propose":[54],"new":[56],"light-weight":[57],"self-supervised":[58,85,120,136],"framework":[60,81,116],"that":[61,82,134],"boost":[63],"supervised":[64,89,144],"performance":[66],"with":[67,158],"minimum":[68,98],"additional":[69,159],"computation":[70],"cost.":[71],"Here,":[72],"introduce":[74],"simple":[76],"flexible":[78],"multi-task":[79],"co-training":[80],"integrates":[83],"task":[86,145],"into":[87],"any":[88],"task.":[90],"Our":[91,131],"approach":[92],"exploits":[93],"pretext":[94],"tasks":[95,137],"incur":[97],"compute":[99],"parameter":[101],"overheads":[102],"minimal":[104],"disruption":[105],"existing":[107],"pipelines.":[109],"We":[110],"demonstrate":[111],"effectiveness":[113],"our":[115],"by":[117],"using":[118],"two":[119],"tasks,":[121],"object":[122],"detection":[123],"panoptic":[125],"segmentation,":[126],"different":[128],"models.":[130],"results":[132],"show":[133],"both":[135],"can":[138],"improve":[139],"accuracy":[141],"and,":[146],"at":[147],"same":[149],"time,":[150],"demonstrates":[151],"strong":[152],"domain":[153],"adaption":[154],"capability":[155],"when":[156],"used":[157]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}