{"id":"https://openalex.org/W2546302380","doi":"https://doi.org/10.1109/iccv.2009.5459469","title":"What is the best multi-stage architecture for object recognition?","display_name":"What is the best multi-stage architecture for object recognition?","publication_year":2009,"publication_date":"2009-09-01","ids":{"openalex":"https://openalex.org/W2546302380","doi":"https://doi.org/10.1109/iccv.2009.5459469","mag":"2546302380"},"language":"en","primary_location":{"id":"doi:10.1109/iccv.2009.5459469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2009.5459469","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE 12th International Conference on Computer Vision","raw_type":"proceedings-article"},"type":"conference-paper","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/A5067360120","display_name":"Kevin Jarrett","orcid":null},"institutions":[{"id":"https://openalex.org/I36672615","display_name":"Courant Institute of Mathematical Sciences","ror":"https://ror.org/037tm7f56","country_code":"US","type":"education","lineage":["https://openalex.org/I36672615","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Jarrett","raw_affiliation_strings":["Courant Institute of Mathematical Sciences, New York University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Courant Institute of Mathematical Sciences, New York University, New York, NY, USA","institution_ids":["https://openalex.org/I36672615","https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090341705","display_name":"Koray Kavukcuoglu","orcid":null},"institutions":[{"id":"https://openalex.org/I36672615","display_name":"Courant Institute of Mathematical Sciences","ror":"https://ror.org/037tm7f56","country_code":"US","type":"education","lineage":["https://openalex.org/I36672615","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Koray Kavukcuoglu","raw_affiliation_strings":["Courant Institute of Mathematical Sciences, New York University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Courant Institute of Mathematical Sciences, New York University, New York, NY, USA","institution_ids":["https://openalex.org/I36672615","https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112227538","display_name":"M. Ranzato","orcid":null},"institutions":[{"id":"https://openalex.org/I36672615","display_name":"Courant Institute of Mathematical Sciences","ror":"https://ror.org/037tm7f56","country_code":"US","type":"education","lineage":["https://openalex.org/I36672615","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marc' Aurelio Ranzato","raw_affiliation_strings":["Courant Institute of Mathematical Sciences, New York University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Courant Institute of Mathematical Sciences, New York University, New York, NY, USA","institution_ids":["https://openalex.org/I36672615","https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001226970","display_name":"Yann LeCun","orcid":null},"institutions":[{"id":"https://openalex.org/I36672615","display_name":"Courant Institute of Mathematical Sciences","ror":"https://ror.org/037tm7f56","country_code":"US","type":"education","lineage":["https://openalex.org/I36672615","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yann LeCun","raw_affiliation_strings":["Courant Institute of Mathematical Sciences, New York University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Courant Institute of Mathematical Sciences, New York University, New York, NY, USA","institution_ids":["https://openalex.org/I36672615","https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2181,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2146","last_page":"2153"},"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":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7610613703727722},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7343178987503052},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.7251129150390625},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7094919085502625},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.6596454381942749},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.633712887763977},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5857126712799072},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5012490749359131},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4894510805606842},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44784748554229736},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4227585196495056},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.4147414565086365},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2692008316516876},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22624891996383667}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7610613703727722},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7343178987503052},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.7251129150390625},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7094919085502625},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.6596454381942749},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.633712887763977},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5857126712799072},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5012490749359131},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4894510805606842},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44784748554229736},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4227585196495056},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.4147414565086365},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2692008316516876},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22624891996383667},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/iccv.2009.5459469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2009.5459469","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE 12th International Conference on Computer Vision","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.158.5759","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.158.5759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://yann.lecun.com/exdb/publis/pdf/jarrett-iccv-09.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.329.3608","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.329.3608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.toronto.edu/~ranzato/publications/architecture-iccv09.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.386.9855","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.386.9855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.nyu.edu/~koray/publis/jarrett-iccv-09.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-05083476v1","is_oa":false,"landing_page_url":"https://hal.science/hal-05083476","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2009 IEEE 12th International Conference on Computer Vision (ICCV), Sep 2009, Kyoto, France. pp.2146-2153, ⟨10.1109/ICCV.2009.5459469⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W101647566","https://openalex.org/W179473274","https://openalex.org/W323291900","https://openalex.org/W1502609557","https://openalex.org/W1556255533","https://openalex.org/W1560253646","https://openalex.org/W1570534137","https://openalex.org/W1584085713","https://openalex.org/W1605353467","https://openalex.org/W1624854622","https://openalex.org/W1818897068","https://openalex.org/W1988570524","https://openalex.org/W1997475636","https://openalex.org/W2010161441","https://openalex.org/W2026942141","https://openalex.org/W2045853963","https://openalex.org/W2053146789","https://openalex.org/W2059749879","https://openalex.org/W2082855665","https://openalex.org/W2095427717","https://openalex.org/W2097018403","https://openalex.org/W2098008728","https://openalex.org/W2100495367","https://openalex.org/W2105464770","https://openalex.org/W2105464873","https://openalex.org/W2110798204","https://openalex.org/W2112504244","https://openalex.org/W2112796928","https://openalex.org/W2113606819","https://openalex.org/W2122808326","https://openalex.org/W2127230474","https://openalex.org/W2130325614","https://openalex.org/W2133257461","https://openalex.org/W2134557905","https://openalex.org/W2139427956","https://openalex.org/W2140262144","https://openalex.org/W2151103935","https://openalex.org/W2155904486","https://openalex.org/W2161969291","https://openalex.org/W2162262658","https://openalex.org/W2162915993","https://openalex.org/W2165828254","https://openalex.org/W2168002178","https://openalex.org/W2171490498","https://openalex.org/W2172174689","https://openalex.org/W2274940154","https://openalex.org/W2278918726","https://openalex.org/W2280828119","https://openalex.org/W2335199846","https://openalex.org/W2437864828","https://openalex.org/W2461672090","https://openalex.org/W2504108613","https://openalex.org/W2908092823","https://openalex.org/W3024197384","https://openalex.org/W4231254085","https://openalex.org/W4232730838","https://openalex.org/W4293652559","https://openalex.org/W6630132114","https://openalex.org/W6674642818","https://openalex.org/W6676481782","https://openalex.org/W6676903177","https://openalex.org/W6679022428","https://openalex.org/W6679718588","https://openalex.org/W6684753728","https://openalex.org/W6685191590"],"related_works":["https://openalex.org/W4386603768","https://openalex.org/W2950475743","https://openalex.org/W2886711096","https://openalex.org/W2750384547","https://openalex.org/W4380078352","https://openalex.org/W3046591097","https://openalex.org/W4389249638","https://openalex.org/W2733410219","https://openalex.org/W2564203852","https://openalex.org/W2552919655"],"abstract_inverted_index":{"In":[0],"many":[1],"recent":[2],"object":[3,139],"recognition":[4,76,140,170],"systems,":[5],"feature":[6,23,33,112,148],"extraction":[7,34,149],"stages":[8,43,51,110,146],"are":[9,39,52,182],"generally":[10],"composed":[11],"of":[12,22,32,111,147],"a":[13,16,160],"filter":[14,72,82],"bank,":[15],"non-linear":[17],"transformation,":[18],"and":[19,125,179,200,214],"some":[20],"sort":[21],"pooling":[24,180],"layer.":[25],"Most":[26,155],"systems":[27],"use":[28],"only":[29],"one":[30,48],"stage":[31],"in":[35,47,54,84],"which":[36],"the":[37,45,67,71,75,81,91,130,176,191,215,221],"filters":[38,46,95,165],"hard-wired,":[40],"or":[41,49,56,87,96],"two":[42,109,145],"where":[44],"both":[50],"learned":[53],"supervised":[55,88,189,205],"unsupervised":[57,86,201],"mode.":[58],"This":[59],"paper":[60],"addresses":[61],"three":[62],"questions:":[63],"1.":[64],"How":[65],"does":[66,79],"non-linearities":[68,121,178],"that":[69,119,122,144,159,175,187],"follow":[70],"banks":[73,83],"influence":[74],"accuracy?":[77],"2.":[78],"learning":[80],"an":[85,106],"manner":[89],"improve":[90],"performance":[92,195],"over":[93],"random":[94,164],"hardwired":[97],"filters?":[98],"3.":[99],"Is":[100],"there":[101],"any":[102],"advantage":[103],"to":[104],"using":[105,120],"architecture":[107],"with":[108,163,188],"extraction,":[113],"rather":[114],"than":[115,153],"one?":[116],"We":[117,142],"show":[118,143,158,186],"include":[123],"rectification":[124],"local":[126],"contrast":[127],"normalization":[128],"is":[129],"single":[131],"most":[132],"important":[133],"ingredient":[134],"for":[135],"good":[136,208],"accuracy":[137,152,209],"on":[138,172,196,210,220],"benchmarks.":[141],"yield":[150,167],"better":[151],"one.":[154],"surprisingly,":[156],"we":[157,185],"two-stage":[161],"system":[162,192],"can":[166],"almost":[168],"63%":[169],"rate":[171,219],"Caltech-101,":[173],"provided":[174],"proper":[177],"layers":[181],"used.":[183],"Finally,":[184],"refinement,":[190],"achieves":[193],"state-of-the-art":[194],"NORB":[197],"dataset":[198,225],"(5.6%)":[199],"pre-training":[202],"followed":[203],"by":[204],"refinement":[206],"produces":[207],"Caltech-101":[211],"(>":[212],"65%),":[213],"lowest":[216],"known":[217],"error":[218],"undistorted,":[222],"unprocessed":[223],"MNIST":[224],"(0.53%).":[226]},"counts_by_year":[{"year":2026,"cited_by_count":17},{"year":2025,"cited_by_count":40},{"year":2024,"cited_by_count":77},{"year":2023,"cited_by_count":102},{"year":2022,"cited_by_count":120},{"year":2021,"cited_by_count":195},{"year":2020,"cited_by_count":213},{"year":2019,"cited_by_count":212},{"year":2018,"cited_by_count":212},{"year":2017,"cited_by_count":218},{"year":2016,"cited_by_count":210},{"year":2015,"cited_by_count":172},{"year":2014,"cited_by_count":139},{"year":2013,"cited_by_count":94},{"year":2012,"cited_by_count":73}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}