{"id":"https://openalex.org/W4391769014","doi":"https://doi.org/10.1109/itsc57777.2023.10422460","title":"Reducing Computer Vision Dataset Size via Selective Sampling","display_name":"Reducing Computer Vision Dataset Size via Selective Sampling","publication_year":2023,"publication_date":"2023-09-24","ids":{"openalex":"https://openalex.org/W4391769014","doi":"https://doi.org/10.1109/itsc57777.2023.10422460"},"language":"en","primary_location":{"id":"doi:10.1109/itsc57777.2023.10422460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc57777.2023.10422460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)","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/A5005506832","display_name":"Hanno Stage","orcid":null},"institutions":[{"id":"https://openalex.org/I143379178","display_name":"FZI Research Center for Information Technology","ror":"https://ror.org/04kdh6x72","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I143379178"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Hanno Stage","raw_affiliation_strings":["FZI Forschungszentrum Informatik,Karlsruhe,Germany","FZI Forschungszentrum Informatik, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"FZI Forschungszentrum Informatik,Karlsruhe,Germany","institution_ids":["https://openalex.org/I143379178"]},{"raw_affiliation_string":"FZI Forschungszentrum Informatik, Karlsruhe, Germany","institution_ids":["https://openalex.org/I143379178"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053061224","display_name":"Lukas Ewecker","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lukas Ewecker","raw_affiliation_strings":["Dr. Ing. h.c. Porsche AG,Weissach,Germany","Dr. Ing. h.c. Porsche AG, Weissach, Germany"],"affiliations":[{"raw_affiliation_string":"Dr. Ing. h.c. Porsche AG,Weissach,Germany","institution_ids":[]},{"raw_affiliation_string":"Dr. Ing. h.c. Porsche AG, Weissach, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051985094","display_name":"Jacob Langner","orcid":null},"institutions":[{"id":"https://openalex.org/I143379178","display_name":"FZI Research Center for Information Technology","ror":"https://ror.org/04kdh6x72","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I143379178"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jacob Langner","raw_affiliation_strings":["FZI Forschungszentrum Informatik,Karlsruhe,Germany","FZI Forschungszentrum Informatik, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"FZI Forschungszentrum Informatik,Karlsruhe,Germany","institution_ids":["https://openalex.org/I143379178"]},{"raw_affiliation_string":"FZI Forschungszentrum Informatik, Karlsruhe, Germany","institution_ids":["https://openalex.org/I143379178"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104242957","display_name":"Tin Stribor Sohn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tin Stribor Sohn","raw_affiliation_strings":["Dr. Ing. h.c. Porsche AG,Weissach,Germany","Dr. Ing. h.c. Porsche AG, Weissach, Germany"],"affiliations":[{"raw_affiliation_string":"Dr. Ing. h.c. Porsche AG,Weissach,Germany","institution_ids":[]},{"raw_affiliation_string":"Dr. Ing. h.c. Porsche AG, Weissach, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027248793","display_name":"Thomas Villmann","orcid":"https://orcid.org/0000-0001-6725-0141"},"institutions":[{"id":"https://openalex.org/I116397343","display_name":"Hochschule Mittweida","ror":"https://ror.org/024ga3r86","country_code":"DE","type":"education","lineage":["https://openalex.org/I116397343"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Villmann","raw_affiliation_strings":["University of Applied Sciences Mittweida (SICIM),Mittweida,Germany","University of Applied Sciences Mittweida (SICIM), Mittweida, Germany"],"affiliations":[{"raw_affiliation_string":"University of Applied Sciences Mittweida (SICIM),Mittweida,Germany","institution_ids":["https://openalex.org/I116397343"]},{"raw_affiliation_string":"University of Applied Sciences Mittweida (SICIM), Mittweida, Germany","institution_ids":["https://openalex.org/I116397343"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080457302","display_name":"Eric Sax","orcid":"https://orcid.org/0000-0003-2567-2340"},"institutions":[{"id":"https://openalex.org/I143379178","display_name":"FZI Research Center for Information Technology","ror":"https://ror.org/04kdh6x72","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I143379178"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Eric Sax","raw_affiliation_strings":["FZI Forschungszentrum Informatik,Karlsruhe,Germany","FZI Forschungszentrum Informatik, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"FZI Forschungszentrum Informatik,Karlsruhe,Germany","institution_ids":["https://openalex.org/I143379178"]},{"raw_affiliation_string":"FZI Forschungszentrum Informatik, Karlsruhe, Germany","institution_ids":["https://openalex.org/I143379178"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005506832"],"corresponding_institution_ids":["https://openalex.org/I143379178"],"apc_list":null,"apc_paid":null,"fwci":0.4343,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70829247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1422","last_page":"1428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.7621999979019165,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.7621999979019165,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.7233999967575073,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.6370000243186951,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6529592275619507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5306711792945862},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5030304789543152},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4895718991756439}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6529592275619507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5306711792945862},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5030304789543152},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4895718991756439},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc57777.2023.10422460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc57777.2023.10422460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1498305593","https://openalex.org/W1977556410","https://openalex.org/W2033626294","https://openalex.org/W2038827046","https://openalex.org/W2049060567","https://openalex.org/W2064210461","https://openalex.org/W2108598243","https://openalex.org/W2166322089","https://openalex.org/W2187098286","https://openalex.org/W2194775991","https://openalex.org/W2535049287","https://openalex.org/W2542065864","https://openalex.org/W2630837129","https://openalex.org/W2887902433","https://openalex.org/W2962963658","https://openalex.org/W2963469388","https://openalex.org/W2963703197","https://openalex.org/W2968893289","https://openalex.org/W3011249019","https://openalex.org/W3016404858","https://openalex.org/W3145543370","https://openalex.org/W3174809957","https://openalex.org/W4205563824","https://openalex.org/W4285118948","https://openalex.org/W4315562626","https://openalex.org/W6668990524","https://openalex.org/W6739696289","https://openalex.org/W6762585180","https://openalex.org/W6776142756","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2058170566","https://openalex.org/W2036807459","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2079911747"],"abstract_inverted_index":{"Developing":[0],"computer":[1,239],"vision":[2,240],"models":[3,210,219,241],"can":[4,149,216],"quickly":[5],"become":[6],"costly.":[7],"On":[8,22],"the":[9,16,23,26,31,34,38,42,72,106,117,179,189],"one":[10],"hand,":[11,25],"this":[12,79,144],"is":[13,28,46,51],"due":[14],"to":[15,85,89,108,123,161,202,237],"often":[17],"large":[18,163],"and":[19,40,61,104,177,245],"complex":[20],"models.":[21],"other":[24,109],"cost":[27,73],"driven":[29],"by":[30,166,197],"size":[32,50],"of":[33,74,170,181,192],"dataset.":[35],"The":[36],"larger":[37,222],"model":[39,76],"dataset,":[41],"more":[43],"compute":[44],"infrastructure":[45],"required.":[47],"Also,":[48,206],"dataset":[49],"a":[52,83,101,127,234],"major":[53],"driver":[54],"for":[55],"storage":[56],"costs":[57],"(e.g.,":[58],"cloud":[59],"storage)":[60],"data":[62,110],"labeling":[63],"effort.":[64],"Yet,":[65],"using":[66,112,193],"smaller":[67,214],"datasets":[68,148,165,195,215,223],"normally":[69],"comes":[70],"at":[71],"inferior":[75],"performance.":[77,249],"In":[78],"paper,":[80],"we":[81,96,120,140,157,187,207,232],"propose":[82],"method":[84,133,160,173,199],"selectively":[86],"sample":[87],"images":[88],"create":[90],"smaller,":[91],"high-quality":[92],"datasets.":[93],"For":[94],"that,":[95,231],"project":[97],"each":[98],"image":[99],"into":[100],"feature":[102],"space":[103],"measure":[105],"similarity":[107,118],"samples":[111],"cosine":[113],"distance.":[114],"Based":[115,184],"on":[116,135,185,212,221],"score,":[119],"decide":[121],"whether":[122],"keep":[124],"or":[125],"discard":[126],"respective":[128],"image.":[129],"We":[130],"demonstrate":[131,188],"our":[132,159,198,213],"based":[134],"two":[136],"use":[137,158],"cases.":[138],"First,":[139],"show":[141],"that":[142,209],"with":[143,152],"approach":[145],"existing":[146,164],"initial":[147],"be":[150],"enriched":[151],"new,":[153],"diverse":[154],"images.":[155,171],"Second,":[156],"reduce":[162],"identifying":[167],"similar":[168],"clusters":[169],"Our":[172],"works":[174],"completely":[175],"unsupervised":[176],"without":[178],"need":[180],"any":[182],"labels.":[183],"experiments":[186],"performance":[190],"improvement":[191],"small":[194],"created":[196,226],"in":[200,242],"comparison":[201],"randomly":[203],"selected":[204],"data.":[205],"find":[208],"trained":[211,220],"even":[217],"outperform":[218],"which":[224],"were":[225],"via":[227],"random":[228],"selection.":[229],"With":[230],"provide":[233],"valuable":[235],"tool":[236],"develop":[238],"resource-constrained":[243],"environments":[244],"sacrifice":[246],"only":[247],"little":[248]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}