{"id":"https://openalex.org/W7166820187","doi":"https://doi.org/10.48550/arxiv.2606.31456","title":"Zero-Shot Quantization for Object Detectors using Off-the-Shelf Generative Models","display_name":"Zero-Shot Quantization for Object Detectors using Off-the-Shelf Generative Models","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W7166820187","doi":"https://doi.org/10.48550/arxiv.2606.31456"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.31456","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.31456","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.31456","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139760557","display_name":"Hyunho Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Hyunho","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139787306","display_name":"Kyomin Hwang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hwang, Kyomin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139798106","display_name":"Hyeonjin Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Hyeonjin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041639553","display_name":"Suyoung Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Suyoung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120648614","display_name":"Sunghyun Wee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wee, Sunghyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139825549","display_name":"Nojun Kwak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kwak, Nojun","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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8787999749183655,"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":0.8787999749183655,"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":0.031599998474121094,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.016100000590085983,"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/quantization","display_name":"Quantization (signal processing)","score":0.6625999808311462},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5295000076293945},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5041000247001648},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.43939998745918274},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4343999922275543},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4203999936580658},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.41760000586509705},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.41190001368522644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6912000179290771},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6625999808311462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5755000114440918},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5295000076293945},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5041000247001648},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.43939998745918274},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4343999922275543},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4203999936580658},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.40790000557899475},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3312999904155731},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2921000123023987},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28929999470710754},{"id":"https://openalex.org/C9083635","wikidata":"https://www.wikidata.org/wiki/Q2133535","display_name":"Noise shaping","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.31456","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.31456","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.31456","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.31456","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6957609057426453,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"an":[1,143,196],"increasing":[2],"number":[3],"of":[4,208],"Object":[5],"Detection":[6],"(OD)":[7],"models":[8,23,66,78],"being":[9],"deployed":[10],"on":[11,35],"edge":[12],"devices,":[13],"Zero-Shot":[14,36],"Quantization":[15],"for":[16,40,67],"OD":[17,41],"(ZSQ-OD)":[18],"aims":[19],"to":[20,26,52,79,96,124,147,156,169,189,199,205],"quantize":[21],"these":[22,138],"when":[24,91],"access":[25],"the":[27,97,110,114,121,125,158,174,201,206],"original":[28,115],"training":[29,43,82],"data":[30],"is":[31,117],"prohibited.":[32],"Existing":[33],"research":[34],"Quantization-Aware":[37],"Training":[38],"(QAT)":[39],"synthesizes":[42],"sets":[44],"through":[45],"noise":[46,171],"optimization.":[47],"However,":[48],"this":[49,59],"approach":[50],"struggles":[51],"maintain":[53],"performance":[54,181],"in":[55,113,182],"low-bit":[56,183],"regions.":[57],"In":[58],"paper,":[60],"we":[61,194],"introduce":[62],"GoodQ":[63,136],"(Generative":[64],"off-the-shelf":[65,76],"object":[68],"detector":[69],"Quantization),":[70],"a":[71,81,93],"QAT":[72,175],"pipeline":[73],"that":[74,89],"utilizes":[75],"generative":[77,94],"construct":[80],"set.":[83],"We":[84],"first":[85],"identify":[86],"three":[87],"challenges":[88,139],"arise":[90],"introducing":[92,142],"model":[95],"ZSQ-OD":[98],"task:":[99],"1)":[100,141],"each":[101],"image":[102],"contains":[103],"dense":[104],"information":[105],"with":[106],"multiple":[107],"instances,":[108],"2)":[109,151],"class-wise":[111],"distribution":[112],"dataset":[116],"imbalanced,":[118],"and":[119,162,186],"3)":[120,163],"pseudo-labels":[122],"assigned":[123],"generated":[126],"images":[127],"can":[128],"potentially":[129],"act":[130],"as":[131],"noisy":[132],"signals":[133],"during":[134],"QAT.":[135],"addresses":[137],"by":[140],"Information-Dense":[144],"Prompting":[145],"strategy":[146],"generate":[148],"multi-instance":[149],"images,":[150],"applying":[152],"Intrinsic":[153],"Distribution-Aware":[154],"Selection":[155],"match":[157],"pretrained":[159],"class":[160],"distribution,":[161],"employing":[164],"Teacher-guided":[165],"Adaptive":[166],"Noise":[167],"Reduction":[168],"mitigate":[170],"arising":[172],"from":[173],"process.":[176],"Our":[177],"framework":[178],"achieves":[179],"state-of-the-art":[180],"ZSQ":[184],"(W4A4)":[185],"extends":[187],"quantization":[188],"extreme":[190],"bit-widths":[191],"(W3A3).":[192],"Furthermore,":[193],"conduct":[195],"extensive":[197],"analysis":[198],"uncover":[200],"underlying":[202],"factors":[203],"contributing":[204],"efficacy":[207],"GoodQ.":[209]},"counts_by_year":[],"updated_date":"2026-07-02T06:18:51.028212","created_date":"2026-07-02T00:00:00"}