{"id":"https://openalex.org/W4285818051","doi":"https://doi.org/10.1109/tnnls.2022.3186855","title":"Temporal Output Discrepancy for Loss Estimation-Based Active Learning","display_name":"Temporal Output Discrepancy for Loss Estimation-Based Active Learning","publication_year":2022,"publication_date":"2022-07-19","ids":{"openalex":"https://openalex.org/W4285818051","doi":"https://doi.org/10.1109/tnnls.2022.3186855","pmid":"https://pubmed.ncbi.nlm.nih.gov/35853066"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3186855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3186855","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2212.10613","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021639720","display_name":"Siyu Huang","orcid":"https://orcid.org/0000-0002-2929-0115"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Siyu Huang","raw_affiliation_strings":["Harvard John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2929-0115","affiliations":[{"raw_affiliation_string":"Harvard John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100656834","display_name":"Tianyang Wang","orcid":"https://orcid.org/0000-0003-3184-0566"},"institutions":[{"id":"https://openalex.org/I184692499","display_name":"Austin Peay State University","ror":"https://ror.org/05tx3bv88","country_code":"US","type":"education","lineage":["https://openalex.org/I184692499"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyang Wang","raw_affiliation_strings":["Department of Computer Science and Information Technology, Austin Peay State University, Clarksville, TN, USA"],"raw_orcid":"https://orcid.org/0000-0003-3184-0566","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Technology, Austin Peay State University, Clarksville, TN, USA","institution_ids":["https://openalex.org/I184692499"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081254155","display_name":"Haoyi Xiong","orcid":"https://orcid.org/0000-0002-5451-3253"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyi Xiong","raw_affiliation_strings":["Big Data Laboratory, Baidu Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Big Data Laboratory, Baidu Research, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024709593","display_name":"Bihan Wen","orcid":"https://orcid.org/0000-0002-6874-6453"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bihan Wen","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Nanyang Ave, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-6874-6453","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Nanyang Ave, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080409305","display_name":"Jun Huan","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Huan","raw_affiliation_strings":["AWS AI Lab, Amazon, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Lab, Amazon, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021332177","display_name":"Dejing Dou","orcid":"https://orcid.org/0000-0003-2949-6874"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dejing Dou","raw_affiliation_strings":["Big Data Laboratory, Baidu Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2949-6874","affiliations":[{"raw_affiliation_string":"Big Data Laboratory, Baidu Research, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5021639720"],"corresponding_institution_ids":["https://openalex.org/I136199984"],"apc_list":null,"apc_paid":null,"fwci":1.3873,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84192142,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"35","issue":"2","first_page":"2109","last_page":"2123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","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/T12072","display_name":"Machine Learning and Algorithms","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/T12535","display_name":"Machine Learning and Data Classification","score":0.9916999936103821,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9828000068664551,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7646664977073669},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.7491352558135986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6428166031837463},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5636985898017883},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5601838231086731},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5207021832466125},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5003957748413086},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.47642645239830017},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44788074493408203},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.426902711391449},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09020152688026428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646664977073669},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.7491352558135986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6428166031837463},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5636985898017883},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5601838231086731},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5207021832466125},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5003957748413086},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.47642645239830017},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44788074493408203},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.426902711391449},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09020152688026428},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tnnls.2022.3186855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3186855","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:35853066","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35853066","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:arXiv.org:2212.10613","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.10613","pdf_url":"https://arxiv.org/pdf/2212.10613","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"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/178104","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/178104","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2212.10613","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.10613","pdf_url":"https://arxiv.org/pdf/2212.10613","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":[{"id":"https://openalex.org/G6093127907","display_name":null,"funder_award_id":"5U54CA225088-03","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W1580210754","https://openalex.org/W1580375566","https://openalex.org/W1975672287","https://openalex.org/W1978633512","https://openalex.org/W2001610032","https://openalex.org/W2008989859","https://openalex.org/W2038967169","https://openalex.org/W2115733720","https://openalex.org/W2117763124","https://openalex.org/W2124244761","https://openalex.org/W2140335411","https://openalex.org/W2140539195","https://openalex.org/W2171671120","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2262342046","https://openalex.org/W2340897893","https://openalex.org/W2460470859","https://openalex.org/W2471138382","https://openalex.org/W2585292948","https://openalex.org/W2593021375","https://openalex.org/W2625559849","https://openalex.org/W2726539084","https://openalex.org/W2735531870","https://openalex.org/W2750023899","https://openalex.org/W2750384547","https://openalex.org/W2777262900","https://openalex.org/W2779649483","https://openalex.org/W2788686132","https://openalex.org/W2798405286","https://openalex.org/W2890546378","https://openalex.org/W2903158431","https://openalex.org/W2949071206","https://openalex.org/W2950725885","https://openalex.org/W2951786554","https://openalex.org/W2956371155","https://openalex.org/W2962850830","https://openalex.org/W2963015987","https://openalex.org/W2963296620","https://openalex.org/W2964159205","https://openalex.org/W2973077827","https://openalex.org/W2984353870","https://openalex.org/W2986514296","https://openalex.org/W3025091470","https://openalex.org/W3035499919","https://openalex.org/W3113055207","https://openalex.org/W3117488606","https://openalex.org/W3118608800","https://openalex.org/W3174894125","https://openalex.org/W3179550234","https://openalex.org/W3184966323","https://openalex.org/W3205626500","https://openalex.org/W4294624582","https://openalex.org/W6617145748","https://openalex.org/W6631190155","https://openalex.org/W6631654266","https://openalex.org/W6635935089","https://openalex.org/W6637162671","https://openalex.org/W6638701278","https://openalex.org/W6675944832","https://openalex.org/W6676834449","https://openalex.org/W6677757056","https://openalex.org/W6677919164","https://openalex.org/W6679227803","https://openalex.org/W6679716015","https://openalex.org/W6733814495","https://openalex.org/W6734269522","https://openalex.org/W6735374517","https://openalex.org/W6735632633","https://openalex.org/W6743688258","https://openalex.org/W6747231328","https://openalex.org/W6748034479","https://openalex.org/W6756615331","https://openalex.org/W6757712183","https://openalex.org/W6762859770","https://openalex.org/W6762953279","https://openalex.org/W6763411897","https://openalex.org/W6764051988","https://openalex.org/W6765807149","https://openalex.org/W6769329967","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W4405124681","https://openalex.org/W1533177136","https://openalex.org/W2073713056"],"abstract_inverted_index":{"While":[0],"deep":[1,84],"learning":[2,33,86,174,206],"succeeds":[3],"in":[4,50,77],"a":[5,44,82,111,236],"wide":[6],"range":[7],"of":[8,17,29,47,107,126,158,183,229,238],"tasks,":[9],"it":[10,147],"highly":[11],"depends":[12],"on":[13,208],"the":[14,27,56,59,69,72,90,96,119,124,142,181,203,226,231],"massive":[15],"collection":[16],"annotated":[18],"data":[19,30,93,166],"which":[20],"is":[21,99,110],"expensive":[22],"and":[23,190,211],"time-consuming.":[24],"To":[25],"lower":[26,75],"cost":[28],"annotation,":[31],"active":[32,85,177,205],"has":[34],"been":[35],"proposed":[36],"to":[37,42,68,101,151,180,224],"interactively":[38],"query":[39],"an":[40,51,163,172],"oracle":[41,91],"annotate":[43],"small":[45],"proportion":[46],"informative":[48,67,153],"samples":[49,60,73],"unlabeled":[52,97,154,165],"dataset.":[53],"Inspired":[54],"by":[55,122,129],"fact":[57],"that":[58,88,117,139,196,219],"with":[61,74],"higher":[62],"loss":[63,121,145],"are":[64,187],"usually":[65],"more":[66],"model":[70,228],"than":[71,202],"loss,":[76],"this":[78],"article":[79],"we":[80,160,217],"present":[81],"novel":[83],"approach":[87,109,198],"queries":[89],"for":[92,176],"annotation":[94],"when":[95],"sample":[98,120,144],"believed":[100],"incorporate":[102],"high":[103],"loss.":[104],"The":[105],"core":[106],"our":[108,185,197],"measurement":[112],"temporal":[113],"output":[114],"discrepancy":[115,125],"(TOD)":[116],"estimates":[118],"evaluating":[123],"outputs":[127],"given":[128],"models":[130],"at":[131],"different":[132],"optimization":[133],"steps.":[134],"Our":[135],"theoretical":[136],"investigation":[137],"shows":[138],"TOD":[140,220],"lower-bounds":[141],"accumulated":[143],"thus":[146],"can":[148,221],"be":[149,222],"used":[150],"select":[152,225],"samples.":[155],"On":[156],"basis":[157],"TOD,":[159,184],"further":[161],"develop":[162],"effective":[164],"sampling":[167],"strategy":[168],"as":[169,171],"well":[170],"unsupervised":[173],"criterion":[175],"learning.":[178],"Due":[179],"simplicity":[182],"methods":[186,207],"efficient,":[188],"flexible,":[189],"task-agnostic.":[191],"Extensive":[192],"experimental":[193],"results":[194],"demonstrate":[195],"achieves":[199],"superior":[200],"performances":[201],"state-of-the-art":[204],"image":[209],"classification":[210],"semantic":[212],"segmentation":[213],"tasks.":[214],"In":[215],"addition,":[216],"show":[218],"utilized":[223],"best":[227],"potentially":[230],"highest":[232],"testing":[233],"accuracy":[234],"from":[235],"pool":[237],"candidate":[239],"models.":[240]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}