{"id":"https://openalex.org/W4414808092","doi":"https://doi.org/10.1145/3787109.3815246","title":"Quantum Probabilistic Label Refining: Enhancing Label Quality for Robust Image Classification","display_name":"Quantum Probabilistic Label Refining: Enhancing Label Quality for Robust Image Classification","publication_year":2026,"publication_date":"2026-06-18","ids":{"openalex":"https://openalex.org/W4414808092","doi":"https://doi.org/10.1145/3787109.3815246"},"language":"en","primary_location":{"id":"doi:10.1145/3787109.3815246","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787109.3815246","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3787109.3815246","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103184212","display_name":"Qi Fang","orcid":"https://orcid.org/0000-0003-4559-6373"},"institutions":[{"id":"https://openalex.org/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fang Qi","raw_affiliation_strings":["Computer Science, Tulane University, New Orleans, LA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1447-0428","affiliations":[{"raw_affiliation_string":"Computer Science, Tulane University, New Orleans, LA, USA","institution_ids":["https://openalex.org/I114832834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101999926","display_name":"Peng Lu","orcid":"https://orcid.org/0000-0002-6621-3258"},"institutions":[{"id":"https://openalex.org/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lu Peng","raw_affiliation_strings":["Computer Science, Tulane University, New Orleans, USA"],"raw_orcid":"https://orcid.org/0000-0003-3545-286X","affiliations":[{"raw_affiliation_string":"Computer Science, Tulane University, New Orleans, USA","institution_ids":["https://openalex.org/I114832834"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054177926","display_name":"Zheng\u2010Ming Ding","orcid":"https://orcid.org/0000-0001-9202-4007"},"institutions":[{"id":"https://openalex.org/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengming Ding","raw_affiliation_strings":["Tulane University, NEW ORLEANS, LA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6994-5278","affiliations":[{"raw_affiliation_string":"Tulane University, NEW ORLEANS, LA, USA","institution_ids":["https://openalex.org/I114832834"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114832834"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00869773,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"298","last_page":"304"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.8773999810218811,"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"}},"topics":[{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.8773999810218811,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.817300021648407,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.6915000081062317},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.6532999873161316},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.5512999892234802},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5113000273704529},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4925999939441681},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.47929999232292175},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.42910000681877136},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.414900004863739},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.3790999948978424}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6915000081062317},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6532999873161316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6389999985694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6373000144958496},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.5512999892234802},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5113000273704529},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5101000070571899},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4925999939441681},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.47929999232292175},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.3790999948978424},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3564999997615814},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.31769999861717224},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C121040770","wikidata":"https://www.wikidata.org/wiki/Q215675","display_name":"Quantum entanglement","level":3,"score":0.29820001125335693},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2856999933719635},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.26460000872612},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C137209882","wikidata":"https://www.wikidata.org/wiki/Q1403517","display_name":"Measurement uncertainty","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25769999623298645},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C27753989","wikidata":"https://www.wikidata.org/wiki/Q284885","display_name":"Superposition principle","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3787109.3815246","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787109.3815246","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.00528","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.00528","pdf_url":"https://arxiv.org/pdf/2510.00528","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,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.00528","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.00528","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3787109.3815246","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787109.3815246","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Learning":[0],"with":[1,111],"softmax":[2],"cross-entropy":[3,113],"on":[4],"one-hot":[5],"labels":[6,49,93,99],"often":[7],"leads":[8],"to":[9,46,80,103,124,163],"overconfident":[10],"predictions":[11],"and":[12,78,117,139,159],"poor":[13],"robustness":[14],"under":[15,128],"noise":[16],"or":[17,62,174],"perturbations.":[18],"Label":[19,153],"smoothing":[20,61],"mitigates":[21],"this":[22],"by":[23],"redistributing":[24],"some":[25],"confidence":[26],"uniformly,":[27],"but":[28],"treats":[29],"all":[30],"samples":[31],"equally,":[32],"ignoring":[33],"intra-class":[34],"variability.":[35],"We":[36],"propose":[37],"a":[38,105],"hybrid":[39],"quantum\u2013classical":[40],"framework":[41],"that":[42,94],"leverages":[43],"quantum":[44,67,74,157],"non-determinism":[45],"refine":[47],"data":[48],"into":[50,72],"probabilistic":[51,91],"ones,":[52],"offering":[53],"more":[54],"nuanced,":[55],"human-like":[56],"uncertainty":[57],"representations":[58],"than":[59],"label":[60],"Bayesian":[63],"approaches.":[64],"A":[65],"variational":[66],"circuit":[68],"(VQC)":[69],"encodes":[70],"inputs":[71],"multi-qubit":[73],"states,":[75],"using":[76],"entanglement":[77],"superposition":[79],"capture":[81],"subtle":[82],"feature":[83],"correlations.":[84],"Measurement":[85],"via":[86,167],"the":[87],"Born":[88],"rule":[89],"extracts":[90],"soft":[92],"reflect":[95,145],"input-specific":[96],"uncertainty.":[97,147],"These":[98],"are":[100],"then":[101],"used":[102],"train":[104],"classical":[106,160],"convolutional":[107],"neural":[108],"network":[109],"(CNN)":[110],"soft-target":[112],"loss.":[114],"On":[115],"MNIST":[116],"Fashion-MNIST,":[118],"our":[119],"method":[120],"improves":[121],"robustness\u2014achieving":[122],"up":[123],"50%":[125],"higher":[126],"accuracy":[127],"noise\u2014while":[129],"maintaining":[130],"competitive":[131],"clean-data":[132],"accuracy.":[133],"It":[134],"also":[135],"enhances":[136],"model":[137],"calibration":[138],"interpretability,":[140],"as":[141],"CNN":[142],"outputs":[143],"better":[144],"quantum-derived":[146],"This":[148],"work":[149],"introduces":[150],"Quantum":[151],"Probabilistic":[152],"Refining,":[154],"which":[155],"bridges":[156],"measurement":[158],"deep":[161],"learning":[162],"enable":[164],"robust":[165],"training":[166],"refined,":[168],"correlation-aware":[169],"labels,":[170],"without":[171],"architectural":[172],"changes":[173],"adversarial":[175],"techniques.":[176]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}