{"id":"https://openalex.org/W1929903369","doi":"https://doi.org/10.1109/cvpr.2015.7298880","title":"Hyper-class augmented and regularized deep learning for fine-grained image classification","display_name":"Hyper-class augmented and regularized deep learning for fine-grained image classification","publication_year":2015,"publication_date":"2015-06-01","ids":{"openalex":"https://openalex.org/W1929903369","doi":"https://doi.org/10.1109/cvpr.2015.7298880","mag":"1929903369"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2015.7298880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2015.7298880","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5102416863","display_name":"Saining Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Saining Xie","raw_affiliation_strings":["University of California, San Diego","University of California. San Diego, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"University of California. San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023288846","display_name":"Tianbao Yang","orcid":"https://orcid.org/0000-0002-7858-5438"},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianbao Yang","raw_affiliation_strings":["Department of Computer Science University of Iowa","Department of Computer Science, University of Iowa, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Iowa","institution_ids":["https://openalex.org/I126307644"]},{"raw_affiliation_string":"Department of Computer Science, University of Iowa, USA#TAB#","institution_ids":["https://openalex.org/I126307644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357613","display_name":"Xiaoyu Wang","orcid":"https://orcid.org/0000-0002-6431-8822"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoyu Wang","raw_affiliation_strings":["Snapchat Research","Snapchat Research, USA"],"affiliations":[{"raw_affiliation_string":"Snapchat Research","institution_ids":["https://openalex.org/I4210142583"]},{"raw_affiliation_string":"Snapchat Research, USA","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112103372","display_name":"Yuanqing Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107353","display_name":"NEC (United States)","ror":"https://ror.org/01v791m31","country_code":"US","type":"company","lineage":["https://openalex.org/I118347220","https://openalex.org/I4210107353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanqing Lin","raw_affiliation_strings":["NEC Laboratories America, Inc","NEC Laboratories America, Inc., USA"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Inc","institution_ids":[]},{"raw_affiliation_string":"NEC Laboratories America, Inc., USA","institution_ids":["https://openalex.org/I4210107353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102416863"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":25.8155,"has_fulltext":false,"cited_by_count":172,"citation_normalized_percentile":{"value":0.99566673,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2645","last_page":"2654"},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.812664270401001},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7504702806472778},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7346965074539185},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6992485523223877},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6453471183776855},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.594121515750885},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5853286981582642},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5357145071029663},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.530627965927124},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5110713243484497},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4975114166736603},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4946243464946747},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.44668444991111755},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.4434272050857544},{"id":"https://openalex.org/keywords/small-data","display_name":"Small data","score":0.423355370759964},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4155419170856476},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.39429616928100586}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.812664270401001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7504702806472778},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7346965074539185},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6992485523223877},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6453471183776855},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.594121515750885},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5853286981582642},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5357145071029663},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.530627965927124},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5110713243484497},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4975114166736603},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4946243464946747},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.44668444991111755},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.4434272050857544},{"id":"https://openalex.org/C2779280203","wikidata":"https://www.wikidata.org/wiki/Q17121211","display_name":"Small data","level":2,"score":0.423355370759964},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4155419170856476},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.39429616928100586},{"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":2,"locations":[{"id":"doi:10.1109/cvpr.2015.7298880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2015.7298880","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.717.6527","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.717.6527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.linyq.com/hyper-cvpr2015.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W56385144","https://openalex.org/W64813323","https://openalex.org/W780950768","https://openalex.org/W1579404597","https://openalex.org/W1597421340","https://openalex.org/W1625255723","https://openalex.org/W1663973292","https://openalex.org/W1686810756","https://openalex.org/W1799366690","https://openalex.org/W1849277567","https://openalex.org/W1986744686","https://openalex.org/W1994213117","https://openalex.org/W1995543189","https://openalex.org/W2009086942","https://openalex.org/W2014102544","https://openalex.org/W2027922120","https://openalex.org/W2045200918","https://openalex.org/W2079629362","https://openalex.org/W2079789819","https://openalex.org/W2094035326","https://openalex.org/W2097018403","https://openalex.org/W2097117768","https://openalex.org/W2098411764","https://openalex.org/W2102605133","https://openalex.org/W2107215754","https://openalex.org/W2108598243","https://openalex.org/W2110765924","https://openalex.org/W2113325037","https://openalex.org/W2117130368","https://openalex.org/W2134270519","https://openalex.org/W2138011018","https://openalex.org/W2141125852","https://openalex.org/W2141659202","https://openalex.org/W2143104527","https://openalex.org/W2145287260","https://openalex.org/W2147414309","https://openalex.org/W2151103935","https://openalex.org/W2155541015","https://openalex.org/W2155839910","https://openalex.org/W2161969291","https://openalex.org/W2163605009","https://openalex.org/W2168356304","https://openalex.org/W2168894214","https://openalex.org/W2169501191","https://openalex.org/W2305141285","https://openalex.org/W2535410496","https://openalex.org/W2913340405","https://openalex.org/W2914746235","https://openalex.org/W2951478888","https://openalex.org/W2963542991","https://openalex.org/W2963606038","https://openalex.org/W3118608800","https://openalex.org/W3143107425","https://openalex.org/W3147600416","https://openalex.org/W4294375521","https://openalex.org/W6629368666","https://openalex.org/W6636494156","https://openalex.org/W6637373629","https://openalex.org/W6638444622","https://openalex.org/W6654164305","https://openalex.org/W6674914833","https://openalex.org/W6676231585","https://openalex.org/W6681010617","https://openalex.org/W6681012330","https://openalex.org/W6682778277","https://openalex.org/W6684191040","https://openalex.org/W6684665197","https://openalex.org/W6684876274","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W4390306690","https://openalex.org/W1969209172","https://openalex.org/W4385572141","https://openalex.org/W4281997472","https://openalex.org/W3046366884","https://openalex.org/W1729894570","https://openalex.org/W4221149036","https://openalex.org/W2554354235","https://openalex.org/W3106263887","https://openalex.org/W4294382023"],"abstract_inverted_index":{"Deep":[0],"convolutional":[1],"neural":[2],"networks":[3],"(CNN)":[4],"have":[5],"seen":[6],"tremendous":[7],"success":[8,174],"in":[9,124],"large-scale":[10,75,192],"generic":[11,17],"object":[12,18],"recognition.":[13],"In":[14,93],"comparison":[15],"with":[16,61],"recognition,":[19],"fine-grained":[20,30,126,163,182],"image":[21,59,142],"classification":[22,91],"(FGIC)":[23],"is":[24,33],"much":[25,34],"more":[26,35],"challenging":[27],"because":[28],"(i)":[29,118],"labeled":[31],"data":[32,64,86,127],"expensive":[36],"to":[37,87],"acquire":[38],"(usually":[39],"requiring":[40],"domain":[41],"expertise);":[42],"(ii)":[43,152],"there":[44],"exists":[45],"large":[46,131],"intra-class":[47],"and":[48,80,128,145,166,186,189],"small":[49,62],"inter-class":[50],"variance.":[51],"Most":[52],"recent":[53],"work":[54],"exploiting":[55,158],"deep":[56,71,108],"CNN":[57,72,109],"for":[58],"recognition":[60,164,169],"training":[63],"adopts":[65],"a":[66,70,74,102,107,130,153,159,191],"simple":[67],"strategy:":[68],"pre-train":[69],"on":[73,82,179,190],"external":[76,139],"dataset":[77,194],"(e.g.,":[78,141],"ImageNet)":[79],"fine-tune":[81],"the":[83,89,97,112,125,147,162,167,173,176],"small-scale":[84,181],"target":[85],"fit":[88],"specific":[90],"task.":[92],"this":[94],"paper,":[95],"beyond":[96],"fine-tuning":[98],"strategy,":[99],"we":[100,196],"propose":[101],"systematic":[103],"framework":[104,178],"of":[105,133,175],"learning":[106,155],"that":[110,195],"addresses":[111],"challenges":[113],"from":[114,136],"two":[115,180],"new":[116],"perspectives:":[117],"identifying":[119],"easily":[120],"annotated":[121],"hyper-classes":[122],"inherent":[123],"acquiring":[129],"number":[132],"hyper-class-labeled":[134],"images":[135],"readily":[137],"available":[138],"sources":[140],"search":[143],"engines),":[144],"formulating":[146],"problem":[148],"into":[149],"multitask":[150],"learning;":[151],"novel":[154],"model":[156,165],"by":[157],"regularization":[160],"between":[161],"hyper-class":[168],"model.":[170],"We":[171],"demonstrate":[172],"proposed":[177],"datasets":[183],"(Stanford":[184],"Dogs":[185],"Stanford":[187],"Cars)":[188],"car":[193],"collected.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":26},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":24},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}