{"id":"https://openalex.org/W2803553068","doi":"https://doi.org/10.48550/arxiv.1805.05809","title":"Efficient end-to-end learning for quantizable representations","display_name":"Efficient end-to-end learning for quantizable representations","publication_year":2018,"publication_date":"2018-05-15","ids":{"openalex":"https://openalex.org/W2803553068","doi":"https://doi.org/10.48550/arxiv.1805.05809","mag":"2803553068"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1805.05809","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.05809","pdf_url":"https://arxiv.org/pdf/1805.05809","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1805.05809","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091794833","display_name":"Yeonwoo Jeong","orcid":"https://orcid.org/0000-0002-4264-8134","observed_orcids":["https://orcid.org/0000-0002-4264-8134"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeong, Yeonwoo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5085451600","display_name":"Hyun Oh Song","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Hyun Oh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2264","last_page":"2273"},"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":0.9965999722480774,"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":0.9965999722480774,"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":0.001500000013038516,"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":0.00039999998989515007,"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/deep-hashing","display_name":"deep hashing","score":0.6110000014305115},{"id":"https://openalex.org/keywords/end-to-end-learning","display_name":"end-to-end learning","score":0.765999972820282},{"id":"https://openalex.org/keywords/similarity-search","display_name":"similarity search","score":0.7120000123977661},{"id":"https://openalex.org/keywords/minimum-cost-flow","display_name":"minimum cost flow","score":0.925000011920929},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"image retrieval","score":0.5630000233650208},{"id":"https://openalex.org/keywords/deep-metric-learning","display_name":"deep metric learning","score":0.5210000276565552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7036074995994568},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6865166425704956},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.6157751083374023},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.6045845150947571},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.58500736951828},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5366721749305725},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.5276134014129639},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.48892226815223694},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4708801209926605},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4686300754547119},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4533391296863556},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4473881423473358},{"id":"https://openalex.org/C138111711","wikidata":"https://www.wikidata.org/wiki/Q478351","display_name":"Double hashing","level":4,"score":0.4451432228088379},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4357690215110779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4313181936740875},{"id":"https://openalex.org/C121610932","wikidata":"https://www.wikidata.org/wiki/Q243754","display_name":"Binary search algorithm","level":3,"score":0.43120405077934265},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3837581276893616},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.3318372368812561},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16044604778289795},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.13614097237586975},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.08159887790679932},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:1805.05809","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.05809","pdf_url":"https://arxiv.org/pdf/1805.05809","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:s-space.snu.ac.kr:10371/179346","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/10371/179346","pdf_url":null,"source":{"id":"https://openalex.org/S4306401345","display_name":"Seoul National University Open Repository (Seoul National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I139264467","host_organization_name":"Seoul National University","host_organization_lineage":["https://openalex.org/I139264467"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"doi:10.48550/arxiv.1805.05809","doi":"https://doi.org/10.48550/arxiv.1805.05809","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1805.05809","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2963678014","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v80/jeong18a/jeong18a.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1805.05809","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.05809","pdf_url":"https://arxiv.org/pdf/1805.05809","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320318942","display_name":"Kakao Brain","ror":"https://ror.org/017agdj19"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2803553068.pdf","grobid_xml":"https://content.openalex.org/works/W2803553068.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W219040644","https://openalex.org/W1522301498","https://openalex.org/W1532325895","https://openalex.org/W1799366690","https://openalex.org/W1910300841","https://openalex.org/W1921523184","https://openalex.org/W1923967535","https://openalex.org/W1956333070","https://openalex.org/W2021354639","https://openalex.org/W2061872629","https://openalex.org/W2068074736","https://openalex.org/W2096733369","https://openalex.org/W2106053110","https://openalex.org/W2113307832","https://openalex.org/W2117539524","https://openalex.org/W2127589108","https://openalex.org/W2138621090","https://openalex.org/W2143516773","https://openalex.org/W2160921898","https://openalex.org/W2176040302","https://openalex.org/W2293824885","https://openalex.org/W2411707397","https://openalex.org/W2551835155","https://openalex.org/W2555897561","https://openalex.org/W2594696540","https://openalex.org/W2613997951","https://openalex.org/W2734694826","https://openalex.org/W2741430497","https://openalex.org/W2963276379","https://openalex.org/W2964121744"],"related_works":["https://openalex.org/W2982425134","https://openalex.org/W2752097935","https://openalex.org/W2956561506","https://openalex.org/W3197358674","https://openalex.org/W2164338181","https://openalex.org/W4224301212","https://openalex.org/W4388514994","https://openalex.org/W1910334602","https://openalex.org/W7100293136","https://openalex.org/W2729435610"],"abstract_inverted_index":{"Embedding":[0],"representation":[1,68],"learning":[2,26,64,115],"via":[3],"neural":[4],"networks":[5],"is":[6,183],"at":[7,185],"the":[8,41,50,60,70,93,100,103,111,122,154,157],"core":[9],"foundation":[10],"of":[11,40,62,95,102,110,156],"modern":[12],"similarity":[13],"based":[14],"search.":[15,179],"While":[16],"much":[17],"effort":[18],"has":[19],"been":[20],"put":[21],"in":[22,92,128,135,161],"developing":[23],"algorithms":[24],"for":[25,31],"binary":[27,72,125],"hamming":[28],"code":[29,74,127,182],"representations":[30],"search":[32,51,90,105,159,173],"efficiency,":[33],"this":[34,56],"still":[35],"requires":[36],"a":[37,65,129,140],"linear":[38,178],"scan":[39],"entire":[42],"dataset":[43],"per":[44],"each":[45],"query":[46],"and":[47,69,149,163,171],"trades":[48],"off":[49],"accuracy":[52,106,160],"through":[53],"binarization.":[54],"To":[55],"end,":[57],"we":[58],"consider":[59],"problem":[61],"directly":[63],"quantizable":[66],"embedding":[67],"sparse":[71,124],"hash":[73,84,126],"end-to-end":[75],"which":[76],"can":[77,131],"be":[78,132],"used":[79],"to":[80,169],"construct":[81],"an":[82],"efficient":[83],"table":[85],"not":[86],"only":[87],"providing":[88,167],"significant":[89],"reduction":[91],"number":[94],"data":[96],"but":[97],"also":[98,118],"achieving":[99],"state":[101,109,155],"art":[104,112,158],"outperforming":[107],"previous":[108],"deep":[113],"metric":[114],"methods.":[116],"We":[117],"show":[119,153],"that":[120],"finding":[121],"optimal":[123],"mini-batch":[130],"computed":[133],"exactly":[134],"polynomial":[136],"time":[137],"by":[138],"solving":[139],"minimum":[141],"cost":[142],"flow":[143],"problem.":[144],"Our":[145],"results":[146],"on":[147,150],"Cifar-100":[148],"ImageNet":[151],"datasets":[152],"precision@k":[162],"NMI":[164],"metrics":[165],"while":[166],"up":[168],"98X":[170],"478X":[172],"speedup":[174],"respectively":[175],"over":[176],"exhaustive":[177],"The":[180],"source":[181],"available":[184],"https://github.com/maestrojeong/Deep-Hash-Table-ICML18":[186]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2018-06-01T00:00:00"}