{"id":"https://openalex.org/W3034764953","doi":"https://doi.org/10.1109/cvpr42600.2020.01385","title":"Improving One-Shot NAS by Suppressing the Posterior Fading","display_name":"Improving One-Shot NAS by Suppressing the Posterior Fading","publication_year":2020,"publication_date":"2020-06-01","ids":{"openalex":"https://openalex.org/W3034764953","doi":"https://doi.org/10.1109/cvpr42600.2020.01385","mag":"3034764953"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr42600.2020.01385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr42600.2020.01385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"preprint","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/A5100631401","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0003-0569-2176"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Li","raw_affiliation_strings":["Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100746862","display_name":"Lin Chen","orcid":"https://orcid.org/0000-0001-5144-7855"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Lin","raw_affiliation_strings":["SenseTime Group Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Group Limited","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063854306","display_name":"Chuming Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuming Li","raw_affiliation_strings":["SenseTime Group Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Group Limited","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755311","display_name":"Ming Sun","orcid":"https://orcid.org/0000-0002-5948-2708"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Sun","raw_affiliation_strings":["SenseTime Group Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Group Limited","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027254893","display_name":"Wei Wu","orcid":"https://orcid.org/0000-0002-2750-6365"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wu","raw_affiliation_strings":["SenseTime Group Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Group Limited","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054033403","display_name":"Junjie Yan","orcid":"https://orcid.org/0000-0001-8016-2277"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Yan","raw_affiliation_strings":["SenseTime Group Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Group Limited","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087818121","display_name":"Wanli Ouyang","orcid":"https://orcid.org/0000-0002-9163-2761"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wanli Ouyang","raw_affiliation_strings":["The University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.6565,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":{"value":0.97588946,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"13833","last_page":"13842"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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":0.9997000098228455,"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/computer-science","display_name":"Computer science","score":0.7957268953323364},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7547427415847778},{"id":"https://openalex.org/keywords/fading","display_name":"Fading","score":0.6299200057983398},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.6238203048706055},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5876288414001465},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5660473704338074},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4996497631072998},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46853604912757874},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4518517851829529},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.43838930130004883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3942549526691437},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37718215584754944},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3226231038570404},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2973860502243042},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0947708785533905},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08541584014892578}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7957268953323364},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7547427415847778},{"id":"https://openalex.org/C81978471","wikidata":"https://www.wikidata.org/wiki/Q1196572","display_name":"Fading","level":3,"score":0.6299200057983398},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.6238203048706055},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5876288414001465},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5660473704338074},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4996497631072998},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46853604912757874},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4518517851829529},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.43838930130004883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3942549526691437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37718215584754944},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3226231038570404},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2973860502243042},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0947708785533905},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08541584014892578},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr42600.2020.01385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr42600.2020.01385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1581066146","https://openalex.org/W1666386643","https://openalex.org/W1861492603","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2553303224","https://openalex.org/W2556833785","https://openalex.org/W2565639579","https://openalex.org/W2594529350","https://openalex.org/W2748513770","https://openalex.org/W2752782242","https://openalex.org/W2767002384","https://openalex.org/W2769653148","https://openalex.org/W2771727678","https://openalex.org/W2796265726","https://openalex.org/W2796438033","https://openalex.org/W2803461142","https://openalex.org/W2810075754","https://openalex.org/W2885820039","https://openalex.org/W2905672847","https://openalex.org/W2905692112","https://openalex.org/W2917028965","https://openalex.org/W2927780566","https://openalex.org/W2930296751","https://openalex.org/W2932077855","https://openalex.org/W2945308135","https://openalex.org/W2949264490","https://openalex.org/W2949533892","https://openalex.org/W2950367719","https://openalex.org/W2951104886","https://openalex.org/W2955051405","https://openalex.org/W2955425717","https://openalex.org/W2960010704","https://openalex.org/W2962740476","https://openalex.org/W2962746461","https://openalex.org/W2962847160","https://openalex.org/W2963037463","https://openalex.org/W2963137684","https://openalex.org/W2963163009","https://openalex.org/W2963778169","https://openalex.org/W2963821229","https://openalex.org/W2963918968","https://openalex.org/W2964259004","https://openalex.org/W2965658867","https://openalex.org/W2967733054","https://openalex.org/W2980137827","https://openalex.org/W2985793077","https://openalex.org/W3009184501","https://openalex.org/W3203915045","https://openalex.org/W4288320011","https://openalex.org/W4295185264","https://openalex.org/W4300687381"],"related_works":["https://openalex.org/W2327053383","https://openalex.org/W2356834760","https://openalex.org/W1964600846","https://openalex.org/W2790025453","https://openalex.org/W2127563499","https://openalex.org/W2030191005","https://openalex.org/W2027568561","https://openalex.org/W1521521035","https://openalex.org/W1865172210","https://openalex.org/W2120897947"],"abstract_inverted_index":{"Neural":[0],"architecture":[1],"search":[2,115],"(NAS)":[3],"has":[4,39],"demonstrated":[5],"much":[6],"success":[7],"in":[8],"automatically":[9],"designing":[10],"effective":[11],"neural":[12],"network":[13],"architectures.":[14],"To":[15,88],"improve":[16],"the":[17,32,77,83,99,114,118],"efficiency":[18],"of":[19,35,73,85],"NAS,":[20],"previous":[21],"approaches":[22,68],"adopt":[23],"weight":[24,64],"sharing":[25,65],"method":[26],"to":[27,97],"force":[28],"all":[29],"models":[30],"share":[31],"same":[33],"set":[34],"weights.":[36,87],"However,":[37],"it":[38],"been":[40],"observed":[41],"that":[42,117],"a":[43,70,94,107],"model":[44],"performing":[45],"better":[46,54],"with":[47],"shared":[48,86],"weights":[49],"does":[50],"not":[51],"necessarily":[52],"perform":[53],"when":[55],"trained":[56],"alone.":[57],"In":[58],"this":[59,90],"paper,":[60],"we":[61,92],"analyse":[62],"existing":[63],"one-shot":[66],"NAS":[67,130],"from":[69],"Bayesian":[71],"point":[72],"view":[74],"and":[75],"identify":[76],"Posterior":[78,128],"Fading":[79],"problem,":[80,91],"which":[81],"compromises":[82],"effectiveness":[84],"alleviate":[89],"present":[93],"novel":[95],"approach":[96],"guide":[98],"parameter":[100],"posterior":[101],"towards":[102],"its":[103],"true":[104],"distribution.":[105],"Moreover,":[106],"hard":[108],"latency":[109,120,138],"constraint":[110,139],"is":[111],"introduced":[112],"during":[113],"so":[116],"desired":[119],"can":[121],"be":[122],"achieved.":[123],"The":[124],"resulted":[125],"method,":[126],"namely":[127],"Convergent":[129],"(PC-NAS),":[131],"achieves":[132],"state-of-the-art":[133],"performance":[134],"under":[135],"standard":[136],"GPU":[137],"on":[140],"ImageNet.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":31},{"year":2020,"cited_by_count":15}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}