{"id":"https://openalex.org/W4385484791","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191400","title":"Multi-Task Meta Learning: learn how to adapt to unseen tasks","display_name":"Multi-Task Meta Learning: learn how to adapt to unseen tasks","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385484791","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191400"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5044246241","display_name":"Richa Upadhyay","orcid":"https://orcid.org/0000-0002-4537-8176"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Richa Upadhyay","raw_affiliation_strings":["Luleå University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Luleå University of Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035834705","display_name":"Prakash Chandra Chhipa","orcid":"https://orcid.org/0000-0002-6903-7552"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prakash Chandra Chhipa","raw_affiliation_strings":["Luleå University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Luleå University of Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010296747","display_name":"Ronald Phlypo","orcid":"https://orcid.org/0000-0003-4310-7994"},"institutions":[{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ronald Phlypo","raw_affiliation_strings":["Université Grenoble Alpes"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université Grenoble Alpes","institution_ids":["https://openalex.org/I899635006"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036975174","display_name":"Rajkumar Saini","orcid":"https://orcid.org/0000-0001-8532-0895"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajkumar Saini","raw_affiliation_strings":["Luleå University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Luleå University of Technology","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073619925","display_name":"Marcus Liwicki","orcid":"https://orcid.org/0000-0003-4029-6574"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcus Liwicki","raw_affiliation_strings":["Luleå University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Luleå University of Technology","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3957,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.908496,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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":0.9997000098228455,"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":0.9997000098228455,"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":0.9941999912261963,"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":0.9721999764442444,"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":0.8050446510314941},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.7554139494895935},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.719103991985321},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6929854154586792},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.6581036448478699},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.6461417078971863},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5815832018852234},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5590834021568298},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.5002284049987793},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4589802324771881},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4223973751068115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8050446510314941},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.7554139494895935},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.719103991985321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6929854154586792},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.6581036448478699},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6461417078971863},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5815832018852234},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5590834021568298},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.5002284049987793},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4589802324771881},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4223973751068115},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04251650v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04251650","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN), Jun 2023, Gold Coast, Australia. pp.1-10, ⟨10.1109/IJCNN54540.2023.10191400⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320336380","display_name":"National Supercomputer Centre, Link\u00f6pings Universitet","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W125693051","https://openalex.org/W169095154","https://openalex.org/W1522301498","https://openalex.org/W1542791059","https://openalex.org/W2092985495","https://openalex.org/W2216125271","https://openalex.org/W2555182955","https://openalex.org/W2604763608","https://openalex.org/W2630837129","https://openalex.org/W2742093937","https://openalex.org/W2753160622","https://openalex.org/W2798441115","https://openalex.org/W2896387979","https://openalex.org/W2908510526","https://openalex.org/W2913340405","https://openalex.org/W2950678851","https://openalex.org/W2951262671","https://openalex.org/W2963430933","https://openalex.org/W2963580001","https://openalex.org/W2963677766","https://openalex.org/W2963877604","https://openalex.org/W2963911235","https://openalex.org/W2964185501","https://openalex.org/W2964247799","https://openalex.org/W2965301120","https://openalex.org/W2966182616","https://openalex.org/W2966461828","https://openalex.org/W2990761674","https://openalex.org/W2991309414","https://openalex.org/W3010436005","https://openalex.org/W3033503043","https://openalex.org/W3085046840","https://openalex.org/W3092053846","https://openalex.org/W3134395475","https://openalex.org/W3153886127","https://openalex.org/W3154934604","https://openalex.org/W3163842339","https://openalex.org/W3191738967","https://openalex.org/W3212653573","https://openalex.org/W3217359438","https://openalex.org/W4251033893","https://openalex.org/W4287027459","https://openalex.org/W4288281388","https://openalex.org/W4294646197","https://openalex.org/W6604254268","https://openalex.org/W6606798317","https://openalex.org/W6631190155","https://openalex.org/W6690067395","https://openalex.org/W6736057607","https://openalex.org/W6738279954","https://openalex.org/W6739696289","https://openalex.org/W6742288159","https://openalex.org/W6743661861","https://openalex.org/W6748136086","https://openalex.org/W6750254146","https://openalex.org/W6751523768","https://openalex.org/W6754628760","https://openalex.org/W6770205404","https://openalex.org/W6774333519","https://openalex.org/W6779247072","https://openalex.org/W6799464151","https://openalex.org/W6803124027"],"related_works":["https://openalex.org/W1488960379","https://openalex.org/W4319075079","https://openalex.org/W3093147807","https://openalex.org/W4287637345","https://openalex.org/W1530810814","https://openalex.org/W3105253998","https://openalex.org/W4287992200","https://openalex.org/W4385484791","https://openalex.org/W4376652622","https://openalex.org/W4226190352"],"abstract_inverted_index":{"This":[0],"work":[1],"proposes":[2],"Multi-task":[3],"Meta":[4],"Learning":[5,12],"(MTML),":[6],"integrating":[7],"two":[8,139,178],"learning":[9,30,120],"paradigms":[10],"Multi-Task":[11],"(MTL)":[13],"and":[14,38,141,145,160,177],"meta":[15,47],"learning,":[16],"to":[17,41,52,67,89,203,216,235],"bring":[18],"together":[19],"the":[20,122,128,146,174,183,187,207,236,244],"best":[21],"of":[22,31,36,46,62,170,180,238],"both":[23],"worlds.":[24],"In":[25,186],"particular,":[26],"it":[27,102,190],"focuses":[28],"simultaneous":[29],"multiple":[32],"tasks,":[33,43,59],"an":[34,97],"element":[35],"MTL":[37],"promptly":[39],"adapting":[40],"new":[42,123],"a":[44,91,110],"quality":[45],"learning.":[48],"It":[49],"is":[50,88,100],"important":[51],"highlight":[53],"that":[54,95,193,200],"we":[55,134,151],"focus":[56],"on":[57,121,138],"heterogeneous":[58],"which":[60,150],"are":[61,76,82],"distinct":[63],"kind,":[64],"in":[65,105,206,219],"contrast":[66],"typically":[68],"considered":[69],"homogeneous":[70],"tasks":[71,75,81,172],"(e.g.,":[72],"if":[73,79],"all":[74,80],"classification":[77],"or":[78,125],"regression":[83],"tasks).":[84],"The":[85,243],"fundamental":[86],"idea":[87],"train":[90],"multi-task":[92],"model,":[93],"such":[94],"when":[96],"unseen":[98],"task":[99,119,124],"introduced,":[101],"can":[103,249],"learn":[104],"fewer":[106],"steps":[107],"whilst":[108],"offering":[109],"performance":[111,231],"at":[112,252],"least":[113],"as":[114,116],"good":[115,225],"conventional":[117],"single":[118],"inclusion":[126],"within":[127],"MTL.":[129],"By":[130],"conducting":[131],"various":[132],"experiments,":[133],"demonstrate":[135],"this":[136],"paradigm":[137],"datasets":[140],"four":[142,171,181],"tasks:":[143],"NYU-v2":[144,175],"taskonomy":[147,184,188],"dataset":[148,176],"for":[149,167,173,182,247],"perform":[152],"semantic":[153],"segmentation,":[154],"depth":[155],"estimation,":[156,159],"surface":[157],"normal":[158],"edge":[161],"detection.":[162],"MTML":[163,212],"achieves":[164],"state-of-the-art":[165],"results":[166],"three":[168],"out":[169,179],"dataset.":[185],"dataset,":[189],"was":[191,214,232],"discovered":[192],"many":[194],"pseudo-labeled":[195],"segmentation":[196],"masks":[197],"lacked":[198],"classes":[199],"were":[201],"expected":[202],"be":[204,217,250],"present":[205],"ground":[208,240],"truth;":[209],"however,":[210],"our":[211],"approach":[213],"found":[215,251],"effective":[218],"detecting":[220],"these":[221],"missing":[222],"classes,":[223],"delivering":[224],"qualitative":[226],"results.":[227],"While,":[228],"quantitatively":[229],"its":[230],"affected":[233],"due":[234],"presence":[237],"incorrect":[239],"truth":[241],"labels.":[242],"source":[245],"code":[246],"reproducibility":[248],"https://github.com/ricupa/MTML-learn-how-to-adapt-to-unseen-tasks.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}