{"id":"https://openalex.org/W3203734261","doi":null,"title":"Data, Assemble: Leveraging Multiple Datasets with Heterogeneous and Partial Labels.","display_name":"Data, Assemble: Leveraging Multiple Datasets with Heterogeneous and Partial Labels.","publication_year":2021,"publication_date":"2021-09-25","ids":{"openalex":"https://openalex.org/W3203734261","mag":"3203734261"},"language":"en","primary_location":{"id":"mag:3203734261","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2109.12265.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.12265.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029251926","display_name":"Mintong Kang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mintong Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081352580","display_name":"Yongyi Lu","orcid":"https://orcid.org/0000-0003-1398-9965","observed_orcids":["https://orcid.org/0000-0003-1398-9965"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongyi Lu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1398-9965","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086706224","display_name":"Alan Yuille","orcid":"https://orcid.org/0000-0001-5207-9249","observed_orcids":["https://orcid.org/0000-0001-5207-9249"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alan Yuille","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5207-9249","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084104975","display_name":"Zongwei Zhou","orcid":"https://orcid.org/0000-0002-3154-9851","observed_orcids":["https://orcid.org/0000-0002-3154-9851","https://orcid.org/0000-0002-4991-8424"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zongwei Zhou","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3154-9851","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.8119999766349792,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.8119999766349792,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.14069999754428864,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.01140000019222498,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/partial-labels","display_name":"partial labels","score":0.5669999718666077},{"id":"https://openalex.org/keywords/heterogeneous-datasets","display_name":"heterogeneous datasets","score":0.7239999771118164},{"id":"https://openalex.org/keywords/multi-dataset-learning","display_name":"multi-dataset learning","score":0.765999972820282},{"id":"https://openalex.org/keywords/pseudo-labeling","display_name":"pseudo-labeling","score":0.7049999833106995},{"id":"https://openalex.org/keywords/consistency-constraints","display_name":"consistency constraints","score":0.796999990940094},{"id":"https://openalex.org/keywords/negative-examples","display_name":"negative examples","score":0.621999979019165},{"id":"https://openalex.org/keywords/rare-disease-detection","display_name":"rare disease detection","score":0.6610000133514404},{"id":"https://openalex.org/keywords/domain-gap","display_name":"domain gap","score":0.5600000023841858},{"id":"https://openalex.org/keywords/feature-aggregation","display_name":"feature aggregation","score":0.45500001311302185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7951871156692505},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.578140914440155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5085552930831909},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49401170015335083},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4930391013622284},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4915667474269867},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4876669645309448},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.47791725397109985},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4624732732772827},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4615260660648346},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4301597476005554},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3287920355796814},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09155702590942383},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3203734261","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2109.12265.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3203734261","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2109.12265.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W2104290444","https://openalex.org/W2112796928","https://openalex.org/W2129068307","https://openalex.org/W2154455818","https://openalex.org/W2340897893","https://openalex.org/W2414711238","https://openalex.org/W2601564443","https://openalex.org/W2611650229","https://openalex.org/W2765312638","https://openalex.org/W2770384498","https://openalex.org/W2793854008","https://openalex.org/W2806321514","https://openalex.org/W2885373832","https://openalex.org/W2886327376","https://openalex.org/W2897806204","https://openalex.org/W2909644922","https://openalex.org/W2910094941","https://openalex.org/W2915126261","https://openalex.org/W2929753309","https://openalex.org/W2946185430","https://openalex.org/W2946236639","https://openalex.org/W2956897601","https://openalex.org/W2962708065","https://openalex.org/W2963446712","https://openalex.org/W2963452532","https://openalex.org/W2963466845","https://openalex.org/W2963942157","https://openalex.org/W2964121744","https://openalex.org/W2964159205","https://openalex.org/W2964227007","https://openalex.org/W2965669393","https://openalex.org/W2970107519","https://openalex.org/W2972407627","https://openalex.org/W2993476821","https://openalex.org/W2995343971","https://openalex.org/W2998348840","https://openalex.org/W3026891415","https://openalex.org/W3030705816","https://openalex.org/W3034421924","https://openalex.org/W3035367255","https://openalex.org/W3085719124","https://openalex.org/W3099570996","https://openalex.org/W3100039191","https://openalex.org/W3106539090","https://openalex.org/W3107917879","https://openalex.org/W3109269658","https://openalex.org/W3117686595","https://openalex.org/W3118608800","https://openalex.org/W3123661268","https://openalex.org/W3127107873","https://openalex.org/W3166595156","https://openalex.org/W3172615411","https://openalex.org/W3172681723","https://openalex.org/W3176031707","https://openalex.org/W3178989684","https://openalex.org/W4288279522"],"related_works":["https://openalex.org/W4386352876","https://openalex.org/W3117686595","https://openalex.org/W6950684484","https://openalex.org/W4399035916","https://openalex.org/W4412558297","https://openalex.org/W4390873131","https://openalex.org/W4386362540","https://openalex.org/W4400199273","https://openalex.org/W4413326490","https://openalex.org/W4413884269"],"abstract_inverted_index":{"The":[0],"success":[1],"of":[2,32,67,78,157,159,169,211],"deep":[3],"learning":[4,36,84,148],"relies":[5],"heavily":[6],"on":[7,131,139,165,218],"large":[8],"datasets":[9,23,135],"with":[10,25,117,232,239],"extensive":[11],"labels,":[12,27,88,225,241],"but":[13],"we":[14,55,89,108,145],"often":[15],"only":[16],"have":[17],"access":[18],"to":[19,62,86,114,121,180,188],"several":[20],"small,":[21],"heterogeneous":[22],"associated":[24],"partial":[26,87,224],"particularly":[28,206],"in":[29,103,198,208],"the":[30,64,82,123,166,195,199,243],"field":[31],"medical":[33],"imaging.":[34],"When":[35],"from":[37,75,149],"multiple":[38,96],"datasets,":[39],"existing":[40,223],"challenges":[41],"include":[42],"incomparable,":[43],"heterogeneous,":[44],"or":[45],"even":[46],"conflicting":[47],"labeling":[48],"protocols":[49],"across":[50,126],"datasets.":[51,79,127],"In":[52],"this":[53],"paper,":[54],"propose":[56],"a":[57,91,104,191,235],"new":[58,163],"initiative--data,":[59],"assemble--which":[60],"aims":[61],"unleash":[63],"full":[65],"potential":[66],"partially":[68],"labeled":[69],"data":[70,74],"and":[71,99,111,120,136,155,172],"enormous":[72],"unlabeled":[73],"an":[76],"assembly":[77],"To":[80],"accommodate":[81],"supervised":[83],"paradigm":[85],"introduce":[90],"dynamic":[92],"adapter":[93],"that":[94,147,233],"encodes":[95],"visual":[97],"tasks":[98],"aggregates":[100],"image":[101],"features":[102],"question-and-answer":[105],"manner.":[106],"Furthermore,":[107],"employ":[109],"pseudo-labeling":[110],"consistency":[112],"constraints":[113],"harness":[115],"images":[116],"missing":[118],"labels":[119],"mitigate":[122],"domain":[124],"gap":[125],"From":[128],"proof-of-concept":[129],"studies":[130],"three":[132],"natural":[133],"imaging":[134],"rigorous":[137],"evaluations":[138],"two":[140],"large-scale":[141],"thorax":[142],"X-ray":[143],"benchmarks,":[144],"discover":[146],"negative":[150,183],"examples":[151,177,184],"facilitates":[152],"both":[153],"classification":[154],"segmentation":[156],"classes":[158],"interest.":[160],"This":[161],"sheds":[162],"light":[164],"computer-aided":[167],"diagnosis":[168],"rare":[170],"diseases":[171,210],"emerging":[173],"pandemics,":[174],"wherein":[175],"positive":[176],"are":[178,185],"hard":[179],"collect,":[181],"yet":[182],"relatively":[186],"easier":[187],"assemble.":[189],"As":[190],"result,":[192],"besides":[193],"exceeding":[194],"prior":[196],"art":[197],"NIH":[200],"ChestXray":[201],"benchmark,":[202],"our":[203,226],"model":[204,227],"is":[205,229],"strong":[207],"identifying":[209],"minority":[212],"classes,":[213],"yielding":[214],"over":[215],"3-point":[216],"improvement":[217],"average.":[219],"Remarkably,":[220],"when":[221],"using":[222,234],"performance":[228],"on-par":[230],"(p>0.05)":[231],"fully":[236],"curated":[237],"dataset":[238],"exhaustive":[240],"eliminating":[242],"need":[244],"for":[245],"additional":[246],"40%":[247],"annotation":[248],"costs.":[249]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-10-11T00:00:00"}