{"id":"https://openalex.org/W4312584410","doi":"https://doi.org/10.1109/icpr56361.2022.9956164","title":"ODG-Q: Robust Quantization via Online Domain Generalization","display_name":"ODG-Q: Robust Quantization via Online Domain Generalization","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4312584410","doi":"https://doi.org/10.1109/icpr56361.2022.9956164"},"language":"en","primary_location":{"id":"doi:10.1109/icpr56361.2022.9956164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956164","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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/A5006519974","display_name":"Chaofan Tao","orcid":"https://orcid.org/0000-0002-6093-0854"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Chaofan Tao","raw_affiliation_strings":["The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072120057","display_name":"Ngai Wong","orcid":"https://orcid.org/0000-0002-3026-0108"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ngai Wong","raw_affiliation_strings":["The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006519974"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.1041,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.32290039,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"32","issue":null,"first_page":"1822","last_page":"1828"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9961000084877014,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9958000183105469,"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/robustness","display_name":"Robustness (evolution)","score":0.7215180993080139},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7054212689399719},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6195656657218933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5823270678520203},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5566688179969788},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5035204291343689},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.42659661173820496},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4170173704624176},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32771432399749756}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7215180993080139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7054212689399719},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6195656657218933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5823270678520203},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5566688179969788},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5035204291343689},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.42659661173820496},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4170173704624176},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32771432399749756},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr56361.2022.9956164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956164","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1779010541","https://openalex.org/W1945616565","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2300242332","https://openalex.org/W2620038827","https://openalex.org/W2774644650","https://openalex.org/W2785952199","https://openalex.org/W2904323922","https://openalex.org/W2907582377","https://openalex.org/W2908392948","https://openalex.org/W2912168260","https://openalex.org/W2913266441","https://openalex.org/W2962851944","https://openalex.org/W2962858109","https://openalex.org/W2962872506","https://openalex.org/W2963744840","https://openalex.org/W2963920068","https://openalex.org/W2964014389","https://openalex.org/W2982479999","https://openalex.org/W3034530016","https://openalex.org/W3088524643","https://openalex.org/W3104433444","https://openalex.org/W3109579921","https://openalex.org/W3118608800","https://openalex.org/W3129764760","https://openalex.org/W3199638224","https://openalex.org/W4288363925","https://openalex.org/W4293846201","https://openalex.org/W4300511536","https://openalex.org/W6640425456","https://openalex.org/W6685133223","https://openalex.org/W6698200048","https://openalex.org/W6739868092","https://openalex.org/W6746402973","https://openalex.org/W6748081988","https://openalex.org/W6757711357","https://openalex.org/W6757949587","https://openalex.org/W6758508162","https://openalex.org/W6758625146","https://openalex.org/W6759129252","https://openalex.org/W6761100157","https://openalex.org/W6783467810","https://openalex.org/W6791089737"],"related_works":["https://openalex.org/W2786764570","https://openalex.org/W4309960894","https://openalex.org/W2728804654","https://openalex.org/W3210882018","https://openalex.org/W2970990331","https://openalex.org/W4379116102","https://openalex.org/W3207178610","https://openalex.org/W3211782752","https://openalex.org/W4309864825","https://openalex.org/W4205547277"],"abstract_inverted_index":{"Quantizing":[0],"neural":[1,137],"networks":[2,138],"to":[3,29,113],"low-bitwidth":[4],"is":[5,27,127],"important":[6],"for":[7,158],"model":[8,21,162],"deployment":[9],"on":[10,86,139,164],"resource-limited":[11],"edge":[12],"hardware.":[13],"Although":[14],"a":[15,19,49,70,109,151],"quantized":[16,42,134],"network":[17],"has":[18],"smaller":[20],"size":[22],"and":[23,38,99,135],"memory":[24],"footprint,":[25],"it":[26],"fragile":[28],"adversarial":[30,67,82],"attacks.":[31,83,147],"However,":[32],"few":[33],"methods":[34],"study":[35],"the":[36,128,159],"robustness":[37,144],"training":[39,110,117],"efficiency":[40],"of":[41,115,154,161],"networks.":[43],"To":[44,121],"this":[45,125],"end,":[46],"we":[47],"propose":[48],"new":[50],"method":[51],"by":[52],"recasting":[53],"robust":[54],"quantization":[55],"as":[56],"an":[57],"online":[58],"domain":[59],"generalization":[60],"problem,":[61],"termed":[62],"ODG-Q,":[63],"which":[64],"generates":[65],"diverse":[66],"data":[68],"at":[69],"low":[71],"cost":[72,111],"during":[73],"training.":[74],"ODG-Q":[75,89,155],"consistently":[76,142],"outperforms":[77],"existing":[78],"works":[79],"against":[80],"various":[81],"For":[84],"example,":[85],"CIFAR-10":[87],"dataset,":[88],"achieves":[90],"49.2%":[91],"average":[92,101],"improvements":[93,102],"under":[94,103,145],"five":[95,104],"common":[96,105],"white-box":[97],"attacks":[98],"21.7%":[100],"black-box":[106],"attacks,":[107],"with":[108],"similar":[112],"that":[114,131,141,156],"natural":[116],"(viz.":[118],"without":[119],"adversaries).":[120],"our":[122],"best":[123],"knowledge,":[124],"work":[126,130],"first":[129],"trains":[132],"both":[133],"binary":[136],"ImageNet":[140],"improves":[143],"different":[146],"We":[148],"also":[149],"provide":[150],"theoretical":[152],"insight":[153],"accounts":[157],"bound":[160],"risk":[163],"attacked":[165],"data.":[166]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}