{"id":"https://openalex.org/W4389989141","doi":"https://doi.org/10.1109/ictai59109.2023.00107","title":"double PT: Enhancing Meta-Learning Performance with Pre-Train and Meta-Pre-Train Processes","display_name":"double PT: Enhancing Meta-Learning Performance with Pre-Train and Meta-Pre-Train Processes","publication_year":2023,"publication_date":"2023-11-06","ids":{"openalex":"https://openalex.org/W4389989141","doi":"https://doi.org/10.1109/ictai59109.2023.00107"},"language":"en","primary_location":{"id":"doi:10.1109/ictai59109.2023.00107","doi":"https://doi.org/10.1109/ictai59109.2023.00107","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ictai59109.2023.00107","pdf_url":null,"source":{"id":"https://openalex.org/S4210176007","display_name":"IEEE International Conference on Tools with Artificial Intelligence (ICTAI)","issn_l":"1082-3409","issn":["1082-3409","2375-0197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 35th International Conference on Tools with Artificial Intelligence (ICTAI)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5025109357","display_name":"Lu Wang","orcid":"https://orcid.org/0000-0002-2923-6047","observed_orcids":["https://orcid.org/0000-0002-2923-6047"]},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Lu Wang","raw_affiliation_strings":["Macao Polytechnic University, Macao, China,Faculty of Applied Sciences,Macao,China","Faculty of Applied Sciences, Macao Polytechnic University, Macao, China, Macao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macao Polytechnic University, Macao, China,Faculty of Applied Sciences,Macao,China","institution_ids":["https://openalex.org/I49835588"]},{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University, Macao, China, Macao, China","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"last","author":{"id":null,"display_name":"K. L. Eddie Law","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"K. L. Eddie Law","raw_affiliation_strings":["Macao Polytechnic University, Macao, China,Faculty of Applied Sciences,Macao,China","Faculty of Applied Sciences, Macao Polytechnic University, Macao, China, Macao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macao Polytechnic University, Macao, China,Faculty of Applied Sciences,Macao,China","institution_ids":["https://openalex.org/I49835588"]},{"raw_affiliation_string":"Faculty of Applied Sciences, Macao Polytechnic University, Macao, China, Macao, China","institution_ids":["https://openalex.org/I49835588"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I49835588"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs/2005.14165","issue":null,"first_page":"688","last_page":"692"},"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":1.0,"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":1.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":9.999999747378752e-05,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0,"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/meta-learning","display_name":"meta-learning","score":0.9819999933242798},{"id":"https://openalex.org/keywords/model-agnostic-meta-learning","display_name":"model-agnostic meta-learning","score":0.800000011920929},{"id":"https://openalex.org/keywords/pretraining","display_name":"pre-training","score":0.8349999785423279},{"id":"https://openalex.org/keywords/feature-representation","display_name":"feature representation","score":0.5370000004768372},{"id":"https://openalex.org/keywords/parameter-efficiency","display_name":"parameter efficiency","score":0.6359999775886536},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.7009999752044678},{"id":"https://openalex.org/keywords/dinov2","display_name":"DINOv2","score":0.9390000104904175},{"id":"https://openalex.org/keywords/task-adaptation","display_name":"task adaptation","score":0.3100000023841858}],"concepts":[{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.7358813285827637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6760240793228149},{"id":"https://openalex.org/C95190672","wikidata":"https://www.wikidata.org/wiki/Q815382","display_name":"Meta-analysis","level":2,"score":0.5073344111442566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32125723361968994},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17425230145454407},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.1037442684173584},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.10255292057991028},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.08664128184318542},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictai59109.2023.00107","doi":"https://doi.org/10.1109/ictai59109.2023.00107","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ictai59109.2023.00107","pdf_url":null,"source":{"id":"https://openalex.org/S4210176007","display_name":"IEEE International Conference on Tools with Artificial Intelligence (ICTAI)","issn_l":"1082-3409","issn":["1082-3409","2375-0197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 35th International Conference on Tools with Artificial Intelligence (ICTAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2601450892","https://openalex.org/W2604763608","https://openalex.org/W2917041815","https://openalex.org/W2974885182","https://openalex.org/W2989756097","https://openalex.org/W2995196103","https://openalex.org/W3015606043","https://openalex.org/W3030163527","https://openalex.org/W3034942609","https://openalex.org/W3159481202","https://openalex.org/W3163842339","https://openalex.org/W3185341429","https://openalex.org/W3204699193","https://openalex.org/W4226530284","https://openalex.org/W4312359569"],"related_works":["https://openalex.org/W3208777316","https://openalex.org/W4382319555","https://openalex.org/W4385826192","https://openalex.org/W3015672537","https://openalex.org/W4281862540","https://openalex.org/W7196945421","https://openalex.org/W4385572141","https://openalex.org/W4386075613","https://openalex.org/W4393010965","https://openalex.org/W4400987213"],"abstract_inverted_index":{"With":[0],"meta-learning,":[1],"models":[2,11,34,61],"are":[3,12],"trained":[4,10,55],"on":[5],"multiple":[6],"tasks,":[7,190],"and":[8,99,168,191,203,205],"resulting":[9],"expected":[13],"to":[14,35,48,62,87,120,134,137,142,207],"be":[15],"capable":[16],"of":[17,52,92,196,215],"\u201c":[18],"learning\u201d":[19],"new":[20,174],"tasks":[21],"effectively.":[22],"MAML":[23,136],"(Model":[24],"Agnostic":[25],"Meta-Learning)":[26],"was":[27],"one":[28],"such":[29],"early":[30],"design":[31],"which":[32,79],"allowed":[33],"reuse":[36],"learned":[37,154],"features,":[38],"but":[39],"with":[40,85],"limited":[41],"performance.":[42],"Pre-training":[43],"is":[44,80],"another":[45],"known":[46],"method":[47,84],"improve":[49],"the":[50,90,110,129,139,144,148,160,164,208,213,219,235,239],"performance":[51],"a":[53,81,116,125],"final":[54],"model.":[56],"Pre-train":[57],"starts":[58],"by":[59,218],"assisting":[60],"seek":[63],"better":[64,69,96,170,193],"initialization":[65],"points,":[66],"thus":[67],"offering":[68],"feature":[70,97,145,156,171],"representations.":[71],"In":[72,128],"this":[73],"paper,":[74],"we":[75,114,132,180],"propose":[76,133],"doublePT":[77,185,202],"(double-pretrain)":[78],"two-stage":[82],"pre-training":[83,118,140,150,198],"goals":[86],"1)":[88],"reduce":[89],"number":[91,214],"parameters,":[93],"2)":[94],"acquire":[95],"representations,":[98,157],"3)":[100],"achieve":[101],"competitive":[102],"overall":[103],"performances":[104],"in":[105,173,228],"different":[106,189,243],"benchmark":[107,244],"measurements.":[108,245],"For":[109],"first":[111],"stage":[112],"operation,":[113],"use":[115,135],"universal":[117],"model":[119,141,151,222,232],"capture":[121],"general":[122,155],"features":[123],"from":[124],"large":[126],"dataset.":[127],"second":[130],"stage,":[131],"fine-tune":[138],"enhance":[143],"adaptability.":[146],"Since":[147],"first-stage":[149],"has":[152,238],"already":[153],"it":[158],"reduces":[159],"training":[161],"activities":[162],"for":[163],"second-stage":[165],"fine-tuning":[166],"operations,":[167],"enables":[169],"extractions":[172],"tasks.":[175],"Validated":[176],"through":[177],"our":[178,183,229],"experiments,":[179],"find":[181],"that":[182,195],"proposed":[184,230],"approach":[186],"fine-tunes":[187],"across":[188,242],"performs":[192],"than":[194,227],"one-stage":[197],"approach.":[199],"Upon":[200],"combining":[201],"DINOv2,":[204],"comparing":[206],"latest":[209],"PMF":[210,220],"meta-learning":[211],"design,":[212],"parameters":[216,226],"required":[217],"pipelining":[221],"needs":[223],"304.8%":[224],"more":[225],"DINOv2+doublePT":[231,236],"design.":[233],"Performance-wise,":[234],"also":[237],"best":[240],"accuracies":[241]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-12-21T00:00:00"}