{"id":"https://openalex.org/W2884397828","doi":"https://doi.org/10.1109/tnnls.2018.2852721","title":"Fine-Grained Image Classification Using Modified DCNNs Trained by Cascaded Softmax and Generalized Large-Margin Losses","display_name":"Fine-Grained Image Classification Using Modified DCNNs Trained by Cascaded Softmax and Generalized Large-Margin Losses","publication_year":2018,"publication_date":"2018-07-24","ids":{"openalex":"https://openalex.org/W2884397828","doi":"https://doi.org/10.1109/tnnls.2018.2852721","mag":"2884397828","pmid":"https://pubmed.ncbi.nlm.nih.gov/30047915"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2018.2852721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2018.2852721","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5067450721","display_name":"Weiwei Shi","orcid":"https://orcid.org/0000-0001-8820-8970"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwei Shi","raw_affiliation_strings":["National Engineering Laboratory for Visual Information Processing and Applications, Xi\u2019an Jiaotong University, Xi\u2019an, China","National Engineering Laboratory for Visual Information Processing and Applications, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-8820-8970","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Visual Information Processing and Applications, Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"National Engineering Laboratory for Visual Information Processing and Applications, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100687952","display_name":"Yihong Gong","orcid":"https://orcid.org/0000-0002-1793-5836"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihong Gong","raw_affiliation_strings":["National Engineering Laboratory for Visual Information Processing and Applications, Xi\u2019an Jiaotong University, Xi\u2019an, China","National Engineering Laboratory for Visual Information Processing and Applications, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-1793-5836","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Visual Information Processing and Applications, Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"National Engineering Laboratory for Visual Information Processing and Applications, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053749425","display_name":"Xiaoyu Tao","orcid":"https://orcid.org/0000-0003-3328-5412"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Tao","raw_affiliation_strings":["National Engineering Laboratory for Visual Information Processing and Applications, Xi\u2019an Jiaotong University, Xi\u2019an, China","National Engineering Laboratory for Visual Information Processing and Applications, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Visual Information Processing and Applications, Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"National Engineering Laboratory for Visual Information Processing and Applications, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101858019","display_name":"De Cheng","orcid":"https://orcid.org/0000-0002-5748-315X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"De Cheng","raw_affiliation_strings":["Department of Computer Science, Xi\u2019an Jiaotong University, Xi\u2019an, China","Department of Computer Science, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-5748-315X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Department of Computer Science, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047405956","display_name":"Nanning Zheng","orcid":"https://orcid.org/0000-0003-1608-8257"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nanning Zheng","raw_affiliation_strings":["National Engineering Laboratory for Visual Information Processing and Applications, Xi\u2019an Jiaotong University, Xi\u2019an, China","National Engineering Laboratory for Visual Information Processing and Applications, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Visual Information Processing and Applications, Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"National Engineering Laboratory for Visual Information Processing and Applications, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":3.0738,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.93983206,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"30","issue":"3","first_page":"683","last_page":"694"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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":0.9987000226974487,"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/softmax-function","display_name":"Softmax function","score":0.9413248300552368},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.7120630741119385},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6996337175369263},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6406310200691223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6180343627929688},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5879770517349243},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5731068849563599},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5525394678115845},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5427409410476685},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5291115641593933},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.503567636013031},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47854334115982056},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.43934375047683716},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2319730520248413}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.9413248300552368},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.7120630741119385},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6996337175369263},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6406310200691223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6180343627929688},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5879770517349243},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5731068849563599},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5525394678115845},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5427409410476685},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5291115641593933},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.503567636013031},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47854334115982056},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.43934375047683716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2319730520248413},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2018.2852721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2018.2852721","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:30047915","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30047915","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3501056997","display_name":null,"funder_award_id":"2015CB351705","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5935354474","display_name":null,"funder_award_id":"61332018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W56385144","https://openalex.org/W196211074","https://openalex.org/W1606858007","https://openalex.org/W1616462885","https://openalex.org/W1686810756","https://openalex.org/W1797268635","https://openalex.org/W1846799578","https://openalex.org/W1928906481","https://openalex.org/W1958236864","https://openalex.org/W1965432148","https://openalex.org/W1972939083","https://openalex.org/W1975517671","https://openalex.org/W1993309459","https://openalex.org/W2027922120","https://openalex.org/W2079789819","https://openalex.org/W2089549033","https://openalex.org/W2096733369","https://openalex.org/W2097117768","https://openalex.org/W2102605133","https://openalex.org/W2104657103","https://openalex.org/W2108598243","https://openalex.org/W2119140755","https://openalex.org/W2135706578","https://openalex.org/W2138011018","https://openalex.org/W2144172034","https://openalex.org/W2155839910","https://openalex.org/W2155893237","https://openalex.org/W2157364932","https://openalex.org/W2162915993","https://openalex.org/W2163605009","https://openalex.org/W2188599881","https://openalex.org/W2194011657","https://openalex.org/W2328317224","https://openalex.org/W2520774990","https://openalex.org/W2548624619","https://openalex.org/W2549097872","https://openalex.org/W2563833337","https://openalex.org/W2573401113","https://openalex.org/W2620694480","https://openalex.org/W2621504606","https://openalex.org/W2624871570","https://openalex.org/W2626361187","https://openalex.org/W2794463555","https://openalex.org/W2964189431","https://openalex.org/W3099206234","https://openalex.org/W6602324145","https://openalex.org/W6607973782","https://openalex.org/W6636412649","https://openalex.org/W6638319203","https://openalex.org/W6640376812","https://openalex.org/W6681239517","https://openalex.org/W6684191040","https://openalex.org/W6726946684","https://openalex.org/W6729073470","https://openalex.org/W6732205034","https://openalex.org/W6739653866"],"related_works":["https://openalex.org/W2982889384","https://openalex.org/W4226227567","https://openalex.org/W2971218105","https://openalex.org/W4287113729","https://openalex.org/W3173314472","https://openalex.org/W3103152812","https://openalex.org/W3120400911","https://openalex.org/W4229443568","https://openalex.org/W2005234362","https://openalex.org/W1997235926"],"abstract_inverted_index":{"We":[0,14],"develop":[1],"a":[2,7,22,66,81],"fine-grained":[3,17,42,108,161,194,201],"image":[4,18,43,109,162,202],"classifier":[5],"using":[6,187],"general":[8,180],"deep":[9],"convolutional":[10],"neural":[11],"network":[12],"(DCNN).":[13],"improve":[15],"the":[16,26,34,41,47,61,74,92,98,103,107,124,133,137,155,159,200,206],"classification":[19,163,203],"accuracy":[20],"of":[21,40,65,106,123,178,208],"DCNN":[23,68,94,128,173,181],"model":[24,33,69,95],"from":[25],"following":[27],"two":[28],"aspects.":[29],"First,":[30],"to":[31,59,90,136,144,150,171],"better":[32],"h":[35,54],"-level":[36],"hierarchical":[37,99],"label":[38,100],"structure":[39,101],"classes":[44,153],"contained":[45],"in":[46,154],"given":[48,67,93],"training":[49],"data":[50,190],"set,":[51],"we":[52,79],"introduce":[53],"fully":[55],"connected":[56],"(fc)":[57],"layers":[58],"replace":[60],"top":[62],"fc":[63],"layer":[64],"and":[70,102,120,167,185,197],"train":[71],"them":[72],"with":[73],"cascaded":[75],"softmax":[76],"loss.":[77],"Second,":[78],"propose":[80],"novel":[82],"loss":[83,113],"function,":[84],"namely,":[85],"generalized":[86],"large-margin":[87],"(GLM)":[88],"loss,":[89],"make":[91],"explicitly":[96,114],"explore":[97],"similarity":[104,119],"regularities":[105],"classes.":[110],"The":[111],"GLM":[112],"not":[115],"only":[116],"reduces":[117],"between-class":[118],"within-class":[121],"variance":[122],"learned":[125],"features":[126],"by":[127],"models":[129,182],"but":[130],"also":[131],"makes":[132],"subclasses":[134],"belonging":[135,149],"same":[138],"coarse":[139,152],"class":[140],"be":[141,169],"more":[142],"similar":[143],"each":[145],"other":[146],"than":[147],"those":[148],"different":[151],"feature":[156],"space.":[157],"Moreover,":[158],"proposed":[160],"framework":[164],"is":[165],"independent":[166],"can":[168],"applied":[170],"any":[172],"structures.":[174],"Comprehensive":[175],"experimental":[176],"evaluations":[177],"several":[179],"(AlexNet,":[183],"GoogLeNet,":[184],"VGG)":[186],"three":[188],"benchmark":[189],"sets":[191],"(Stanford":[192],"car,":[193],"visual":[195],"classification-aircraft,":[196],"CUB-200-2011)":[198],"for":[199],"task":[204],"demonstrate":[205],"effectiveness":[207],"our":[209],"method.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":9}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}