{"id":"https://openalex.org/W7126088953","doi":"https://doi.org/10.1109/icfsp67350.2025.11353810","title":"Optimizing Dataset Quality and Diversity in Neural Networks: A Study of the Vendi Score","display_name":"Optimizing Dataset Quality and Diversity in Neural Networks: A Study of the Vendi Score","publication_year":2025,"publication_date":"2025-09-10","ids":{"openalex":"https://openalex.org/W7126088953","doi":"https://doi.org/10.1109/icfsp67350.2025.11353810"},"language":"en","primary_location":{"id":"doi:10.1109/icfsp67350.2025.11353810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icfsp67350.2025.11353810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 10th International Conference on Frontiers of Signal Processing (ICFSP)","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/A5124157034","display_name":"Sebastian Krebs","orcid":null},"institutions":[{"id":"https://openalex.org/I9649716","display_name":"HTWG Hochschule Konstanz - Technik, Wirtschaft und Gestaltung","ror":"https://ror.org/051qw9f78","country_code":"DE","type":"education","lineage":["https://openalex.org/I9649716"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Krebs","raw_affiliation_strings":["University of Applied Sciences HTWG,Konstanz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Applied Sciences HTWG,Konstanz","institution_ids":["https://openalex.org/I9649716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007852853","display_name":"Alexander Bernhardt","orcid":"https://orcid.org/0000-0002-2572-5062"},"institutions":[{"id":"https://openalex.org/I9649716","display_name":"HTWG Hochschule Konstanz - Technik, Wirtschaft und Gestaltung","ror":"https://ror.org/051qw9f78","country_code":"DE","type":"education","lineage":["https://openalex.org/I9649716"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Bernhardt","raw_affiliation_strings":["University of Applied Sciences HTWG,Konstanz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Applied Sciences HTWG,Konstanz","institution_ids":["https://openalex.org/I9649716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111966129","display_name":"Bastian Goldl\u00fccke","orcid":null},"institutions":[{"id":"https://openalex.org/I189712700","display_name":"University of Konstanz","ror":"https://ror.org/0546hnb39","country_code":"DE","type":"education","lineage":["https://openalex.org/I189712700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bastian Goldl\u00fccke","raw_affiliation_strings":["University of Konstanz,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Konstanz,Department of Computer Science","institution_ids":["https://openalex.org/I189712700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124255360","display_name":"Christopher Knievel","orcid":null},"institutions":[{"id":"https://openalex.org/I9649716","display_name":"HTWG Hochschule Konstanz - Technik, Wirtschaft und Gestaltung","ror":"https://ror.org/051qw9f78","country_code":"DE","type":"education","lineage":["https://openalex.org/I9649716"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christopher Knievel","raw_affiliation_strings":["University of Applied Sciences HTWG,Konstanz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Applied Sciences HTWG,Konstanz","institution_ids":["https://openalex.org/I9649716"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87707394,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"134","last_page":"138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8748999834060669,"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":0.8748999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.018799999728798866,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.012199999764561653,"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/weighting","display_name":"Weighting","score":0.6226999759674072},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5645999908447266},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5457000136375427},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4970000088214874},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.49000000953674316},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47290000319480896},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46860000491142273},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4634999930858612},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.423799991607666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.714900016784668},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6226999759674072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6017000079154968},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5716000199317932},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5645999908447266},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5457000136375427},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5360000133514404},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4970000088214874},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.49000000953674316},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47290000319480896},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4634999930858612},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.33869999647140503},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.2985000014305115},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icfsp67350.2025.11353810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icfsp67350.2025.11353810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 10th International Conference on Frontiers of Signal Processing (ICFSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:elib.uni-konstanz.de-htwg:5696","is_oa":false,"landing_page_url":"https://opus.htwg-konstanz.de/frontdoor/index/index/docId/5696","pdf_url":null,"source":{"id":"https://openalex.org/S4306400170","display_name":"URN-Resolver at the German National Library (German National Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2802635041","host_organization_name":"Technische Informationsbibliothek (TIB)","host_organization_lineage":["https://openalex.org/I2802635041"],"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":"conferenceobject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1968535060","https://openalex.org/W1995875735","https://openalex.org/W2022485595","https://openalex.org/W2026465529","https://openalex.org/W2046013022","https://openalex.org/W2116044718","https://openalex.org/W2118376687","https://openalex.org/W4231566795"],"related_works":[],"abstract_inverted_index":{"We":[0],"investigate":[1],"methods":[2],"for":[3,38,57,64,148,191,225],"evaluating":[4],"and":[5,23,40,89,115,162,213,220],"optimizing":[6],"dataset":[7,42,87,206,228],"quality":[8,60],"in":[9,47,107,208],"the":[10,19,27,54,77,92,151,174,197,202,215,218],"context":[11],"of":[12,79,94,173,196,205,217],"image-based":[13],"object":[14,96],"detection":[15],"tasks,":[16],"focusing":[17],"on":[18,76,145],"Vendi":[20,29],"Score":[21,30],"(VS)":[22],"its":[24],"enhanced":[25],"variant,":[26],"quality-weighted":[28],"(qVS).":[31],"These":[32,199],"metrics":[33],"provide":[34],"a":[35,44,58,71,108,119,192],"robust":[36],"framework":[37],"assessing":[39],"improving":[41],"diversity,":[43],"critical":[45],"factor":[46],"effectively":[48],"training":[49,182],"neural":[50,210],"networks.":[51],"In":[52],"particular,":[53],"qVS":[55,152,221],"allows":[56,190],"customizable":[59],"measure":[61],"to":[62,81,84,90,103,127,159,166,230],"account":[63],"dataset-specific":[65],"characteristics.In":[66],"this":[67,183],"paper,":[68],"we":[69],"introduce":[70],"specific":[72],"weighting":[73],"function":[74],"based":[75],"ratio":[78],"objects":[80,106],"total":[82],"images":[83],"ensure":[85],"balanced":[86],"composition":[88,229],"emphasize":[91],"importance":[93],"diverse":[95,171],"representations.":[97],"Feature":[98],"extraction":[99],"techniques":[100],"are":[101],"employed":[102],"represent":[104],"image":[105],"unified":[109],"feature":[110],"space,":[111],"enabling":[112],"similarity":[113],"calculations":[114],"diversity":[116,134,149,207],"assessments.":[117],"Additionally,":[118],"multi":[120],"objective":[121],"genetic":[122],"algorithm":[123],"(MOGA)":[124],"is":[125],"utilized":[126],"optimize":[128],"datasets":[129,172],"across":[130],"multiple":[131],"classes,":[132],"maximizing":[133],"while":[135],"maintaining":[136],"class":[137],"balance.Our":[138],"experimental":[139],"results":[140],"demonstrate":[141],"that":[142],"models":[143],"trained":[144],"subsets":[146,157],"optimized":[147],"using":[150],"achieve":[153],"improved":[154],"performance.":[155],"Diverse":[156],"lead":[158],"higher":[160],"precision":[161],"generalization":[163],"capabilities":[164],"compared":[165],"randomly":[167],"selected":[168],"or":[169],"less":[170],"same":[175],"size.":[176],"Especially":[177],"when":[178],"sampling":[179],"minibatches":[180],"during":[181],"method":[184],"may":[185],"prove":[186],"beneficial,":[187],"as":[188,222],"it":[189],"more":[193],"representative":[194],"sample":[195],"dataset.":[198],"findings":[200],"underscore":[201],"pivotal":[203],"role":[204],"enhancing":[209],"network":[211],"performance":[212],"highlight":[214],"utility":[216],"VS":[219],"valuable":[223],"tools":[224],"strategically":[226],"shaping":[227],"improve":[231],"outcomes.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-30T00:00:00"}