{"id":"https://openalex.org/W3212572379","doi":"https://doi.org/10.1109/mlsp52302.2021.9596284","title":"Few-Shot Learning Via Dependency Maximization and Instance Discriminant Analysis","display_name":"Few-Shot Learning Via Dependency Maximization and Instance Discriminant Analysis","publication_year":2021,"publication_date":"2021-10-25","ids":{"openalex":"https://openalex.org/W3212572379","doi":"https://doi.org/10.1109/mlsp52302.2021.9596284","mag":"3212572379"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp52302.2021.9596284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp52302.2021.9596284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5055234106","display_name":"Zejiang Hou","orcid":"https://orcid.org/0000-0002-6836-8288"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zejiang Hou","raw_affiliation_strings":["Princeton University"],"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072714962","display_name":"Sun\u2010Yuan Kung","orcid":"https://orcid.org/0000-0002-7314-0720"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sun-Yuan Kung","raw_affiliation_strings":["Princeton University"],"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055234106"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":0.136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56495077,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9714000225067139,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9358000159263611,"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":0.7505159378051758},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7294173836708069},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5870352387428284},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5789894461631775},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.5017416477203369},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.4900006353855133},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4456237852573395},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4232249855995178},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4181942343711853},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14862743020057678},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12125647068023682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505159378051758},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7294173836708069},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5870352387428284},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5789894461631775},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5017416477203369},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.4900006353855133},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4456237852573395},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4232249855995178},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4181942343711853},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14862743020057678},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12125647068023682},{"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/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp52302.2021.9596284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp52302.2021.9596284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7099999785423279,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1638081485","https://openalex.org/W1797268635","https://openalex.org/W2022809245","https://openalex.org/W2122922389","https://openalex.org/W2601450892","https://openalex.org/W2604763608","https://openalex.org/W2753160622","https://openalex.org/W2787035179","https://openalex.org/W2963070905","https://openalex.org/W2963341924","https://openalex.org/W2963741406","https://openalex.org/W2964026991","https://openalex.org/W2964105864","https://openalex.org/W2964112702","https://openalex.org/W2964137095","https://openalex.org/W2971071159","https://openalex.org/W2994661711","https://openalex.org/W2995589713","https://openalex.org/W3009081299","https://openalex.org/W3012255272","https://openalex.org/W3020429927","https://openalex.org/W3034312118","https://openalex.org/W3035143213","https://openalex.org/W3035302051","https://openalex.org/W3035531117","https://openalex.org/W3081382462","https://openalex.org/W3108009835","https://openalex.org/W3108878460","https://openalex.org/W3110214837","https://openalex.org/W4236617288","https://openalex.org/W6717697761","https://openalex.org/W6735236233","https://openalex.org/W6736057607","https://openalex.org/W6743661861","https://openalex.org/W6748284727","https://openalex.org/W6753311412","https://openalex.org/W6758126075","https://openalex.org/W6761378032","https://openalex.org/W6762818971","https://openalex.org/W6768230505","https://openalex.org/W6771260093","https://openalex.org/W6780205758","https://openalex.org/W6782534648"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W1481704333"],"abstract_inverted_index":{"We":[0,114,163],"study":[1],"the":[2,30,34,65,81,85,90,94,107,111,117,122,137,145,156,160,165,169,172,178,189],"few-shot":[3,51,66,70],"learning":[4,40],"(FSL)":[5],"problem,":[6],"where":[7,33],"a":[8,48,57,75],"model":[9,35,119,157],"learns":[10],"to":[11,29,46,60,120,135,154],"recognize":[12],"new":[13,49],"objects":[14],"with":[15,106],"extremely":[16],"few":[17],"labeled":[18],"training":[19,42],"data":[20,63,100,174],"per":[21],"category.":[22],"Most":[23],"of":[24,84,97,139],"previous":[25,193],"FSL":[26,183],"approaches":[27],"resort":[28],"meta-learning":[31],"paradigm,":[32],"accumulates":[36],"inductive":[37],"bias":[38],"through":[39],"many":[41],"tasks":[43],"so":[44],"as":[45,158],"solve":[47],"unseen":[50],"task.":[52],"In":[53],"contrast,":[54],"we":[55,73,129],"propose":[56,74,130],"simple":[58],"approach":[59],"exploit":[61],"unlabeled":[62,99,126,173],"accompanying":[64],"task":[67],"for":[68,124,171],"improving":[69],"performance.":[71],"Firstly,":[72],"Dependency":[76],"Maximization":[77],"method":[78,191],"based":[79],"on":[80,196],"Hilbert-Schmidt":[82],"norm":[83],"cross-covariance":[86],"operator,":[87],"which":[88],"maximizes":[89],"statistical":[91],"dependency":[92],"between":[93],"embedded":[95],"feature":[96],"those":[98,125],"and":[101,143,181,205],"their":[102],"label":[103],"predictions,":[104],"together":[105],"supervised":[108],"loss":[109],"over":[110],"support":[112,152],"set.":[113],"then":[115],"use":[116],"obtained":[118],"infer":[121],"pseudo-labels":[123,170],"data.":[127],"Furthermore,":[128],"an":[131,150],"Instance":[132],"Discriminant":[133],"Analysis":[134],"evaluate":[136],"credibility":[138],"each":[140],"pseudo-labeled":[141],"example":[142],"select":[144],"most":[146],"faithful":[147],"ones":[148],"into":[149],"augmented":[151],"set":[153],"retrain":[155],"in":[159],"first":[161],"step.":[162],"iterate":[164],"above":[166],"process":[167],"until":[168],"become":[175],"stable.":[176],"Following":[177],"standard":[179],"transductive":[180],"semi-supervised":[182],"setting,":[184],"our":[185],"experiments":[186],"show":[187],"that":[188],"proposed":[190],"outperforms":[192],"state-of-the-art":[194],"methods":[195],"four":[197],"widely":[198],"used":[199],"benchmarks,":[200],"including":[201],"mini-ImageNet,":[202],"tiered-ImageNet,":[203],"CUB,":[204],"CIFARFS.":[206]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}