{"id":"https://openalex.org/W3153445072","doi":"https://doi.org/10.17615/7f2f-4f29","title":"LEARNING TO ADAPT FROM FEW EXAMPLES","display_name":"LEARNING TO ADAPT FROM FEW EXAMPLES","publication_year":2020,"publication_date":"2020-02-11","ids":{"openalex":"https://openalex.org/W3153445072","doi":"https://doi.org/10.17615/7f2f-4f29","mag":"3153445072"},"language":"en","primary_location":{"id":"mag:3153445072","is_oa":false,"landing_page_url":"https://cdr.lib.unc.edu/concern/dissertations/f7623j22p","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.17615/7f2f-4f29","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013897558","display_name":"Eunbyung Park","orcid":"https://orcid.org/0000-0003-4071-2814"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Park, Eunbyung","raw_affiliation_strings":["University of North Carolina at Chapel Hill"],"affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5013897558"],"corresponding_institution_ids":["https://openalex.org/I114027177"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19408054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T11448","display_name":"Face recognition and analysis","score":0.23880000412464142,"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/T11448","display_name":"Face recognition and analysis","score":0.23880000412464142,"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":0.21610000729560852,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.19339999556541443,"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":0.4266817569732666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4266817569732666}],"mesh":[],"locations_count":2,"locations":[{"id":"mag:3153445072","is_oa":false,"landing_page_url":"https://cdr.lib.unc.edu/concern/dissertations/f7623j22p","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null},{"id":"doi:10.17615/7f2f-4f29","is_oa":true,"landing_page_url":"https://doi.org/10.17615/7f2f-4f29","pdf_url":null,"source":{"id":"https://openalex.org/S7407051488","display_name":"UNC Libraries","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"thesis"}],"best_oa_location":{"id":"doi:10.17615/7f2f-4f29","is_oa":true,"landing_page_url":"https://doi.org/10.17615/7f2f-4f29","pdf_url":null,"source":{"id":"https://openalex.org/S7407051488","display_name":"UNC Libraries","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"thesis"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899138465","https://openalex.org/W2582605192","https://openalex.org/W3175361714","https://openalex.org/W70275994","https://openalex.org/W2953748542","https://openalex.org/W1696165702","https://openalex.org/W3157573123","https://openalex.org/W2126291255","https://openalex.org/W2966907664","https://openalex.org/W34759514","https://openalex.org/W1559084219","https://openalex.org/W2283952483","https://openalex.org/W2996514457","https://openalex.org/W2991842365","https://openalex.org/W2073221076","https://openalex.org/W3148047180","https://openalex.org/W2954850701","https://openalex.org/W2124267516","https://openalex.org/W2199916546","https://openalex.org/W3201424076"],"abstract_inverted_index":{"Despite":[0],"huge":[1],"progress":[2],"in":[3,53,92,118,191,276,290,319,333,369,372],"artificial":[4],"intelligence,":[5],"the":[6,24,44,54,87,102,122,143,157,182,189,192,197,214,217,228,231,264,277,294,302,326,329,334,344,355,395,404],"ability":[7],"to":[8,37,85,112,137,187,204,297,354,412],"quickly":[9,109],"learn":[10],"from":[11],"few":[12,272],"examples":[13,273],"is":[14,80,99,166,267,296,323],"still":[15],"far":[16],"short":[17],"of":[18,20,26,56,104,142,216,230,237,279,287,301,308,311,328,363,375,394],"that":[19,48,71,107,128,156,168,196,258],"a":[21,115,205,235,284,305,313,361,370],"human.":[22],"With":[23],"goal":[25,103,295],"building":[27],"machines":[28],"with":[29,39,234,263,360],"this":[30,226],"capability,":[31],"learning-to-learn":[32],"or":[33,145],"meta-learning":[34,51],"has":[35],"begun":[36],"emerge":[38],"promising":[40,249],"results.":[41],"I":[42],"present":[43],"effectiveness":[45],"and":[46,62,134,153,163,176,225,248,336,342,365,382,390,400],"techniques":[47],"improve":[49,160],"existing":[50,413],"methods":[52],"context":[55,278],"visual":[57,68,392],"object":[58,69,289,303],"tracking,":[59],"few-shot":[60,63],"classification,":[61],"reinforcement":[64,252],"learning":[65,98,169,186,253],"setup.":[66],"The":[67,77,96],"trackers":[70,159],"use":[72],"online":[73,93],"adaptation":[74],"are":[75,129,223,274,339],"improved.":[76],"core":[78],"contribution":[79],"an":[81,256,288,291,299,320],"offline":[82],"meta-learning-based":[83],"method":[84,406],"adjust":[86],"initial":[88],"deep":[89,105],"networks":[90,106],"used":[91],"adaptation-based":[94],"tracking.":[95],"meta":[97],"driven":[100],"by":[101],"can":[108,172],"be":[110],"adapted":[111],"robustly":[113],"model":[114,178],"particular":[116],"target":[117],"future":[119,132],"frames.":[120],"Ideally":[121],"resulting":[123],"models":[124,270],"focus":[125],"on":[126,149,181,245,251],"features":[127],"useful":[130],"for":[131],"frames,":[133],"avoid":[135],"overfitting":[136],"background":[138],"clutter,":[139],"small":[140],"parts":[141,327],"target,":[144],"noise.":[146],"Experimental":[147,240],"results":[148,241,250,368,402,410],"standard":[150],"benchmarks,":[151],"OTB2015":[152],"VOT2016,":[154],"show":[155,242,403],"meta-learned":[158],"speed,":[161],"accuracy,":[162],"robustness.":[164],"It":[165],"observed":[167],"curvature":[170,218,266],"information":[171,317],"achieve":[173,200],"better":[174,201,260,409],"generalization":[175,202,261],"fast":[177],"adaptation.":[179],"Based":[180],"model-agnostic":[183],"meta-learner":[184],"(MAML),":[185],"transform":[188],"gradients":[190,199],"inner":[193],"optimization":[194],"such":[195,379],"transformed":[198],"performance":[203,262],"new":[206,356],"task.":[207,351],"For":[208],"training":[209,359],"large":[210],"scale":[211],"neural":[212],"networks,":[213],"decomposition":[215],"matrix":[219],"into":[220],"smaller":[221],"matrices":[222],"proposed":[224,405],"capture":[227],"dependencies":[229],"model's":[232],"parameters":[233],"series":[236],"tensor":[238],"products.":[239],"significant":[243],"improvements":[244],"classification":[246],"tasks":[247],"tasks.":[254],"Finally,":[255],"analysis":[257],"explains":[259],"meta-trained":[265],"presented.":[268],"Generative":[269],"given":[271],"explored":[275],"novel":[280,337,376],"3D":[281],"view":[282,286,377],"synthesis---given":[283],"single":[285],"arbitrary":[292],"pose,":[293],"synthesize":[298],"image":[300,322,349],"after":[304],"specified":[306],"transformation":[307],"viewpoint.":[309],"Instead":[310],"taking":[312],"`blank":[314],"slate'":[315],"approach,":[316],"presented":[318],"input":[321,335,396],"used.":[324],"First,":[325],"geometry":[330],"visible":[331],"both":[332],"views":[338],"explicitly":[340],"inferred,":[341],"then":[343],"remaining":[345],"synthesis":[346,378],"problem":[347],"becomes":[348],"completion":[350],"In":[352],"addition":[353],"network":[357],"structure,":[358],"combination":[362],"adversarial":[364],"perceptual":[366],"loss":[367],"reduction":[371],"common":[373],"artifacts":[374],"as":[380],"distortions":[381],"holes,":[383],"while":[384],"successfully":[385],"generating":[386],"high":[387],"frequency":[388],"details":[389],"preserving":[391],"aspects":[393],"image.":[397],"Both":[398],"qualitative":[399],"quantitative":[401],"achieves":[407],"significantly":[408],"compared":[411],"methods.":[414]},"counts_by_year":[],"updated_date":"2026-03-03T08:47:05.690250","created_date":"2025-10-10T00:00:00"}