{"id":"https://openalex.org/W2415630426","doi":"https://doi.org/10.1109/acpr.2015.7486549","title":"How to initialize the CNN for small datasets: Extracting discriminative filters from pre-trained model","display_name":"How to initialize the CNN for small datasets: Extracting discriminative filters from pre-trained model","publication_year":2015,"publication_date":"2015-11-01","ids":{"openalex":"https://openalex.org/W2415630426","doi":"https://doi.org/10.1109/acpr.2015.7486549","mag":"2415630426"},"language":"en","primary_location":{"id":"doi:10.1109/acpr.2015.7486549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acpr.2015.7486549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","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/A5087863930","display_name":"Guanwen Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Guanwen Zhang","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080180020","display_name":"Jien Kato","orcid":"https://orcid.org/0000-0002-0196-4405"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jien Kato","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445368","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0003-3511-0288"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111458376","display_name":"Kenji Mase","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenji Mase","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5087863930"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":0.1841,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.62935915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"479","last_page":"483"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9977999925613403,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9976999759674072,"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/discriminative-model","display_name":"Discriminative model","score":0.9007314443588257},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7937791347503662},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6947789192199707},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6486726403236389},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6409247517585754},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5172515511512756}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9007314443588257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7937791347503662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6947789192199707},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6486726403236389},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6409247517585754},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5172515511512756},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acpr.2015.7486549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acpr.2015.7486549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1892735011","https://openalex.org/W2033178790","https://openalex.org/W2097117768","https://openalex.org/W2102605133","https://openalex.org/W2113606819","https://openalex.org/W2118858186","https://openalex.org/W2162741153","https://openalex.org/W2163605009","https://openalex.org/W2168894214","https://openalex.org/W2335728318","https://openalex.org/W2408243929","https://openalex.org/W2936995161","https://openalex.org/W2950094539","https://openalex.org/W2963606038","https://openalex.org/W3118608800","https://openalex.org/W6631943919","https://openalex.org/W6637373629","https://openalex.org/W6639574400","https://openalex.org/W6674914833","https://openalex.org/W6676903177","https://openalex.org/W6677919164","https://openalex.org/W6684191040","https://openalex.org/W6684665197","https://openalex.org/W6703116779","https://openalex.org/W6713722401","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2404514746","https://openalex.org/W1652783584","https://openalex.org/W2082783427","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,21],"study":[4],"how":[5],"to":[6,23,70],"initialize":[7],"the":[8,28,36,62,83,95,98],"convolutional":[9],"neural":[10],"network":[11],"(CNN)":[12],"model":[13,30],"for":[14,31],"training":[15],"on":[16,82],"a":[17,32],"small":[18],"dataset.":[19],"Specially,":[20],"try":[22],"extract":[24],"discriminative":[25],"filters":[26],"from":[27],"pre-trained":[29],"target":[33],"task.":[34],"On":[35],"basis":[37],"of":[38,97],"relative":[39],"entropy":[40],"and":[41,50,65,73,80,87],"linear":[42],"reconstruction,":[43],"two":[44],"methods,":[45],"Minimum":[46,51],"Entropy":[47],"Loss":[48],"(MEL)":[49],"Reconstruction":[52],"Error":[53],"(MRE),":[54],"are":[55,68],"proposed.":[56],"The":[57,91],"CNN":[58],"models":[59],"initialized":[60],"by":[61],"proposed":[63,99],"MEL":[64,79],"MRE":[66,81],"methods":[67],"able":[69],"converge":[71],"fast":[72],"achieve":[74],"better":[75],"accuracy.":[76],"We":[77],"evaluate":[78],"CIFAR10,":[84],"CIFAR100,":[85],"SVHN,":[86],"STL-10":[88],"public":[89],"datasets.":[90],"consistent":[92],"performances":[93],"demonstrate":[94],"advantages":[96],"methods.":[100]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}