{"id":"https://openalex.org/W2967587448","doi":null,"title":"Pseudo-task Regularization for ConvNet Transfer Learning.","display_name":"Pseudo-task Regularization for ConvNet Transfer Learning.","publication_year":2019,"publication_date":"2019-08-16","ids":{"openalex":"https://openalex.org/W2967587448","mag":"2967587448"},"language":"en","primary_location":{"id":"mag:2967587448","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1908.05997v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1908.05997v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101408030","display_name":"Yang Zhong","orcid":"https://orcid.org/0000-0002-6439-6564","observed_orcids":["https://orcid.org/0000-0002-6439-6564"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong Yang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4452-4108","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5054834085","display_name":"Atsuto Maki","orcid":"https://orcid.org/0000-0002-4266-6746","observed_orcids":["https://orcid.org/0000-0002-4266-6746"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atsuto Maki","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4266-6746","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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/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/transfer-learning","display_name":"transfer learning","score":0.9800000190734863},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.8289999961853027},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"multi-objective optimization","score":0.7689999938011169},{"id":"https://openalex.org/keywords/gradient-norm","display_name":"gradient norm","score":0.5979999899864197}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.8390845060348511},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6821857690811157},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6654411554336548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5925362706184387},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5150547027587891},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5127728581428528}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2967587448","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1908.05997v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2967587448","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1908.05997v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1576445103","https://openalex.org/W1686810756","https://openalex.org/W1834627138","https://openalex.org/W1849277567","https://openalex.org/W1861492603","https://openalex.org/W2038765747","https://openalex.org/W2087681821","https://openalex.org/W2095705004","https://openalex.org/W2099471712","https://openalex.org/W2108598243","https://openalex.org/W2152161678","https://openalex.org/W2155541015","https://openalex.org/W2159291411","https://openalex.org/W2161381512","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2200124539","https://openalex.org/W2203224402","https://openalex.org/W2562986790","https://openalex.org/W2759703061","https://openalex.org/W2786462443","https://openalex.org/W2949117887","https://openalex.org/W2949667497","https://openalex.org/W2950179405","https://openalex.org/W2950220847","https://openalex.org/W2951093852","https://openalex.org/W2962743139","https://openalex.org/W3021931813","https://openalex.org/W3118608800","https://openalex.org/W4231090517"],"related_works":["https://openalex.org/W3034273919","https://openalex.org/W3000574192","https://openalex.org/W3090231108","https://openalex.org/W2972887897","https://openalex.org/W2736375505","https://openalex.org/W2990812820","https://openalex.org/W2910745941","https://openalex.org/W3208576249","https://openalex.org/W7006069377","https://openalex.org/W3112728147"],"abstract_inverted_index":{"This":[0],"paper":[1,153],"is":[2,144,181],"about":[3],"regularizing":[4],"deep":[5],"convolutional":[6],"networks":[7],"(ConvNets)":[8],"based":[9,186],"on":[10,106,115,131,167,187],"an":[11,64,158],"adaptive":[12],"multi-objective":[13],"framework":[14],"for":[15,129,134,142,163],"transfer":[16],"learning":[17],"with":[18],"limited":[19],"training":[20,47],"data":[21],"in":[22,31,179],"the":[23,38,46,50,104,119,132,188,192,196],"target":[24,51,193],"domain.":[25],"Recent":[26],"advances":[27],"of":[28,40,151,176,191],"ConvNets":[29],"regularization":[30,42,143,164,177],"this":[32,152],"context":[33],"are":[34,111],"commonly":[35],"due":[36],"to":[37,92,96,118],"use":[39],"additional":[41],"objectives.":[43],"They":[44],"guide":[45],"away":[48],"from":[49],"task":[52,141],"using":[53],"some":[54],"concrete":[55,68,168],"tasks.":[56],"Unlike":[57],"those":[58],"related":[59],"approaches,":[60],"we":[61,79],"report":[62],"that":[63],"objective":[65,194],"without":[66,165],"a":[67,75,87,97,116,127,135,146],"goal":[69],"can":[70],"serve":[71],"surprisingly":[72],"well":[73],"as":[74],"regularizer.":[76],"In":[77],"particular,":[78],"demonstrate":[80],"Pseudo-task":[81],"Regularization":[82],"(PtR)":[83],"which":[84],"dynamically":[85,182],"regularizes":[86],"network":[88],"by":[89,109],"simply":[90],"attempting":[91],"regress":[93],"image":[94],"representations":[95],"pseudo-target":[98],"during":[99],"fine-tuning.":[100],"Through":[101],"numerous":[102],"experiments,":[103],"improvements":[105],"classification":[107],"accuracy":[108],"PtR":[110,156,180],"shown":[112],"greater":[113],"or":[114,170],"par":[117],"recent":[120],"state-of-the-art":[121],"methods.":[122],"These":[123],"results":[124],"also":[125],"indicate":[126],"room":[128],"rethinking":[130],"requirements":[133],"regularizer,":[136],"i.e.,":[137],"if":[138],"specifically":[139],"designed":[140],"indeed":[145],"key":[147],"ingredient.":[148],"The":[149],"contributions":[150],"are:":[154],"a)":[155],"provides":[157],"effective":[159],"and":[160,184,195],"efficient":[161],"alternative":[162],"dependence":[166],"tasks":[169],"extra":[171],"data;":[172],"b)":[173],"desired":[174],"strength":[175],"effect":[178],"adjusted":[183],"maintained":[185],"gradient":[189],"norms":[190],"pseudo-task.":[197]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-08-22T00:00:00"}