{"id":"https://openalex.org/W3011408986","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023037","title":"Small-Sample Image Classification Method of Combining Prototype and Margin Learning","display_name":"Small-Sample Image Classification Method of Combining Prototype and Margin Learning","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011408986","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023037","mag":"3011408986"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5100758186","display_name":"Xiaoxu Li","orcid":"https://orcid.org/0000-0001-8833-9401"},"institutions":[{"id":"https://openalex.org/I22716506","display_name":"Lanzhou University of Technology","ror":"https://ror.org/03panb555","country_code":"CN","type":"education","lineage":["https://openalex.org/I22716506"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoxu Li","raw_affiliation_strings":["Lanzhou University of Technology, Lanzhou, China"],"affiliations":[{"raw_affiliation_string":"Lanzhou University of Technology, Lanzhou, China","institution_ids":["https://openalex.org/I22716506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082206371","display_name":"Liyun Yu","orcid":"https://orcid.org/0000-0002-4293-3066"},"institutions":[{"id":"https://openalex.org/I22716506","display_name":"Lanzhou University of Technology","ror":"https://ror.org/03panb555","country_code":"CN","type":"education","lineage":["https://openalex.org/I22716506"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyun Yu","raw_affiliation_strings":["Lanzhou University of Technology, Lanzhou, China"],"affiliations":[{"raw_affiliation_string":"Lanzhou University of Technology, Lanzhou, China","institution_ids":["https://openalex.org/I22716506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101752375","display_name":"Jie Cao","orcid":"https://orcid.org/0000-0003-0481-5170"},"institutions":[{"id":"https://openalex.org/I22716506","display_name":"Lanzhou University of Technology","ror":"https://ror.org/03panb555","country_code":"CN","type":"education","lineage":["https://openalex.org/I22716506"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Cao","raw_affiliation_strings":["Lanzhou University of Technology, Lanzhou, China"],"affiliations":[{"raw_affiliation_string":"Lanzhou University of Technology, Lanzhou, China","institution_ids":["https://openalex.org/I22716506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007417490","display_name":"Dongliang Chang","orcid":"https://orcid.org/0000-0002-4081-3001"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongliang Chang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, China, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039812471","display_name":"Zhanyu Ma","orcid":"https://orcid.org/0000-0003-2950-2488"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanyu Ma","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, China, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100377352","display_name":"Nian Liu","orcid":"https://orcid.org/0000-0002-0825-6081"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nian Liu","raw_affiliation_strings":["South-to-North Water Diversion Middle Route Information Technology Co., Ltd., China"],"affiliations":[{"raw_affiliation_string":"South-to-North Water Diversion Middle Route Information Technology Co., Ltd., China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100758186"],"corresponding_institution_ids":["https://openalex.org/I22716506"],"apc_list":null,"apc_paid":null,"fwci":0.2024,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.56947528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"521","issue":null,"first_page":"91","last_page":"95"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983999729156494,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983999729156494,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9975000023841858,"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":0.996399998664856,"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/overfitting","display_name":"Overfitting","score":0.9151772260665894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.8026646375656128},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7477690577507019},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6740716695785522},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6043389439582825},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.586172878742218},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5757037997245789},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.558966338634491},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5397366881370544},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5208054780960083},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5062998533248901},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.49732163548469543},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.31547003984451294}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9151772260665894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8026646375656128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7477690577507019},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6740716695785522},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6043389439582825},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.586172878742218},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5757037997245789},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.558966338634491},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5397366881370544},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5208054780960083},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5062998533248901},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.49732163548469543},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31547003984451294},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W1566135517","https://openalex.org/W1686810756","https://openalex.org/W2019787708","https://openalex.org/W2062227835","https://openalex.org/W2066757459","https://openalex.org/W2068238590","https://openalex.org/W2163605009","https://openalex.org/W2164921999","https://openalex.org/W2166049352","https://openalex.org/W2242218935","https://openalex.org/W2342611082","https://openalex.org/W2592340788","https://openalex.org/W2605344185","https://openalex.org/W2613763509","https://openalex.org/W2725995746","https://openalex.org/W2738853914","https://openalex.org/W2745610371","https://openalex.org/W2919115771","https://openalex.org/W2951696358","https://openalex.org/W2951970475","https://openalex.org/W4232478844","https://openalex.org/W6600213771","https://openalex.org/W6684191040","https://openalex.org/W6737781455","https://openalex.org/W6740217354"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W1038900426","https://openalex.org/W3128011703","https://openalex.org/W2005234362","https://openalex.org/W1997235926"],"abstract_inverted_index":{"Image":[0],"classification":[1,21,114],"is":[2,46,62,136,146],"a":[3,63,107,137,147],"fundamental":[4],"and":[5,14,56,69,143,164,176],"important":[6],"task":[7],"in":[8],"the":[9,48,71,74,77,95,125,128,144,161,165,170],"field":[10],"of":[11,73,98,127],"computer":[12],"vision":[13],"artificial":[15],"intelligence.":[16],"In":[17,102],"recent":[18],"years,":[19],"image":[20,41,91,113,159],"has":[22,57,173],"made":[23],"breakthrough":[24],"progress":[25],"based":[26,81,119,139,149],"on":[27,30,39,82,89,120,140,150,156],"deep":[28,49,83,99],"learning":[29,61],"large-scale":[31],"datasets.":[32],"However,":[33],"it":[34],"still":[35,86],"exits":[36],"big":[37,58,96],"challenges":[38],"small-sample":[40,54,90,112,158],"data.":[42],"The":[43,116,153],"main":[44],"difficulty":[45],"that":[47,169],"neural":[50,84,100],"network":[51,85,130],"easily":[52],"overfit":[53,88],"data":[55,92],"variance.":[59],"Ensemble":[60],"good":[64],"way":[65],"to":[66,94,131],"overcome":[67],"overfitting":[68],"reduce":[70],"variance":[72],"model;":[75],"however,":[76],"existing":[78],"ensemble":[79,109],"methods":[80],"could":[87],"due":[93],"randomness":[97],"network.":[101],"this":[103],"paper,":[104],"we":[105,123],"propose":[106],"new":[108],"method":[110,118,172],"for":[111],"tasks.":[115],"proposed":[117,171],"VGG16":[121,129],"network,":[122],"modified":[124],"structure":[126],"two":[132,157],"branches,":[133],"one":[134],"branch":[135],"classifier":[138,148],"prototype":[141],"learning,":[142],"other":[145,180],"margin":[151],"learning.":[152],"experimental":[154],"results":[155],"datasets,":[160],"LabelMe":[162],"dataset":[163],"Caltech101":[166],"dataset,":[167],"show":[168],"better":[174],"performance":[175],"higher":[177],"stability":[178],"than":[179],"referred":[181],"methods.":[182]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}