{"id":"https://openalex.org/W3180303049","doi":"https://doi.org/10.1109/cvpr46437.2021.00533","title":"Deep Stable Learning for Out-Of-Distribution Generalization","display_name":"Deep Stable Learning for Out-Of-Distribution Generalization","publication_year":2021,"publication_date":"2021-06-01","ids":{"openalex":"https://openalex.org/W3180303049","doi":"https://doi.org/10.1109/cvpr46437.2021.00533","mag":"3180303049"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr46437.2021.00533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.00533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5054379354","display_name":"Xingxuan Zhang","orcid":"https://orcid.org/0009-0002-4788-1127"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xingxuan Zhang","raw_affiliation_strings":["Department of Computer Science, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009228005","display_name":"Peng Cui","orcid":"https://orcid.org/0000-0003-2957-8511"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Cui","raw_affiliation_strings":["Beijing Key Lab of Networked Multimedia","Department of Computer Science, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Lab of Networked Multimedia","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061888153","display_name":"Renzhe Xu","orcid":"https://orcid.org/0000-0001-8418-0034"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renzhe Xu","raw_affiliation_strings":["Department of Computer Science, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004704989","display_name":"Linjun Zhou","orcid":"https://orcid.org/0000-0001-5978-4602"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linjun Zhou","raw_affiliation_strings":["Department of Computer Science, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101790419","display_name":"Yue He","orcid":"https://orcid.org/0000-0001-6776-4679"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue He","raw_affiliation_strings":["Department of Computer Science, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112662608","display_name":"Zheyan Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheyan Shen","raw_affiliation_strings":["Department of Computer Science, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5054379354"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":26.1726,"has_fulltext":false,"cited_by_count":260,"citation_normalized_percentile":{"value":0.99704167,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5368","last_page":"5378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9995999932289124,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9995999932289124,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9991999864578247,"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":0.9983000159263611,"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/generalization","display_name":"Generalization","score":0.8181169033050537},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7936674356460571},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7219858169555664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7196056842803955},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6860733032226562},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.6640571355819702},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6307533383369446},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5852488279342651},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.581528902053833},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4689452350139618},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4410623610019684},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.43877533078193665},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3832924962043762},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1696014702320099}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8181169033050537},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7936674356460571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7219858169555664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7196056842803955},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6860733032226562},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6640571355819702},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6307533383369446},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5852488279342651},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.581528902053833},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4689452350139618},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4410623610019684},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.43877533078193665},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3832924962043762},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1696014702320099},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr46437.2021.00533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.00533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":118,"referenced_works":["https://openalex.org/W1731081199","https://openalex.org/W1852255964","https://openalex.org/W1882958252","https://openalex.org/W1920962657","https://openalex.org/W2031342017","https://openalex.org/W2100600008","https://openalex.org/W2108598243","https://openalex.org/W2112552549","https://openalex.org/W2144902422","https://openalex.org/W2155858138","https://openalex.org/W2157801062","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2201792562","https://openalex.org/W2626639386","https://openalex.org/W2749492999","https://openalex.org/W2751134959","https://openalex.org/W2758584002","https://openalex.org/W2763549966","https://openalex.org/W2765424254","https://openalex.org/W2767614983","https://openalex.org/W2781474777","https://openalex.org/W2787226294","https://openalex.org/W2790149178","https://openalex.org/W2798658180","https://openalex.org/W2806187986","https://openalex.org/W2807992610","https://openalex.org/W2889965839","https://openalex.org/W2891612330","https://openalex.org/W2892623062","https://openalex.org/W2906202001","https://openalex.org/W2907264311","https://openalex.org/W2907520152","https://openalex.org/W2914607694","https://openalex.org/W2945033152","https://openalex.org/W2949737767","https://openalex.org/W2953073956","https://openalex.org/W2953494151","https://openalex.org/W2953937638","https://openalex.org/W2958360136","https://openalex.org/W2962900737","https://openalex.org/W2963043696","https://openalex.org/W2963060032","https://openalex.org/W2963118547","https://openalex.org/W2963305465","https://openalex.org/W2963528347","https://openalex.org/W2963625477","https://openalex.org/W2963734296","https://openalex.org/W2963826681","https://openalex.org/W2963838962","https://openalex.org/W2964132737","https://openalex.org/W2964260444","https://openalex.org/W2966200864","https://openalex.org/W2970119729","https://openalex.org/W2975059128","https://openalex.org/W2981368934","https://openalex.org/W2997591099","https://openalex.org/W2997746169","https://openalex.org/W2998653622","https://openalex.org/W2998712190","https://openalex.org/W3007592798","https://openalex.org/W3013459733","https://openalex.org/W3033161486","https://openalex.org/W3034373371","https://openalex.org/W3035037113","https://openalex.org/W3035198372","https://openalex.org/W3036085734","https://openalex.org/W3038585207","https://openalex.org/W3095799614","https://openalex.org/W3102032239","https://openalex.org/W3103557498","https://openalex.org/W3106845355","https://openalex.org/W3109635165","https://openalex.org/W3109831211","https://openalex.org/W3123400235","https://openalex.org/W4288287305","https://openalex.org/W4288404646","https://openalex.org/W4288617013","https://openalex.org/W4290473204","https://openalex.org/W4293861706","https://openalex.org/W4297730339","https://openalex.org/W6637618735","https://openalex.org/W6639105354","https://openalex.org/W6639480849","https://openalex.org/W6675134017","https://openalex.org/W6676726796","https://openalex.org/W6681302627","https://openalex.org/W6682834636","https://openalex.org/W6683124652","https://openalex.org/W6684191040","https://openalex.org/W6693617700","https://openalex.org/W6739575509","https://openalex.org/W6743634349","https://openalex.org/W6743928203","https://openalex.org/W6745134051","https://openalex.org/W6746195791","https://openalex.org/W6747227044","https://openalex.org/W6748426227","https://openalex.org/W6752160200","https://openalex.org/W6754038005","https://openalex.org/W6754669440","https://openalex.org/W6755191029","https://openalex.org/W6757555829","https://openalex.org/W6757712578","https://openalex.org/W6759517920","https://openalex.org/W6762970624","https://openalex.org/W6764990469","https://openalex.org/W6765285020","https://openalex.org/W6766295588","https://openalex.org/W6767145319","https://openalex.org/W6767680423","https://openalex.org/W6767852397","https://openalex.org/W6774630179","https://openalex.org/W6774827837","https://openalex.org/W6779466609","https://openalex.org/W6779676466","https://openalex.org/W6779681340","https://openalex.org/W6780174346"],"related_works":["https://openalex.org/W2618574054","https://openalex.org/W4385524141","https://openalex.org/W3018979822","https://openalex.org/W3026616975","https://openalex.org/W4288018014","https://openalex.org/W4297776111","https://openalex.org/W2989784533","https://openalex.org/W2996058201","https://openalex.org/W2946347869","https://openalex.org/W3127679336"],"abstract_inverted_index":{"Approaches":[0],"based":[1],"on":[2,112,130,142],"deep":[3,41,100],"neural":[4],"networks":[5],"have":[6],"achieved":[7],"striking":[8],"performance":[9],"when":[10],"testing":[11,34],"data":[12,15,35,52],"and":[13,33,119,150],"training":[14,32,51,96],"share":[16],"similar":[17],"distribution,":[18],"but":[19],"can":[20],"significantly":[21],"fail":[22],"otherwise.":[23],"Therefore,":[24],"eliminating":[25],"the":[26,47,57,76,88,113,125,154],"impact":[27],"of":[28,50,61,75,104,127,156],"distribution":[29,132,143],"shifts":[30],"between":[31,90,116],"is":[36],"crucial":[37],"for":[38,95],"building":[39],"performance-promising":[40],"models.":[42],"Conventional":[43],"methods":[44],"assume":[45],"either":[46],"known":[48],"heterogeneity":[49],"(e.g.":[53],"domain":[54],"labels)":[55],"or":[56],"approximately":[58],"equal":[59],"capacities":[60],"different":[62],"domains.":[63],"In":[64],"this":[65,84],"paper,":[66],"we":[67,152],"consider":[68],"a":[69],"more":[70,111],"challenging":[71],"case":[72],"where":[73],"neither":[74],"above":[77],"assumptions":[78],"holds.":[79],"We":[80],"propose":[81],"to":[82],"address":[83],"problem":[85],"by":[86],"removing":[87],"dependencies":[89],"features":[91,118],"via":[92],"learning":[93],"weights":[94],"samples,":[97],"which":[98],"helps":[99],"models":[101],"get":[102],"rid":[103],"spurious":[105],"correlations":[106],"and,":[107],"in":[108],"turn,":[109],"concentrate":[110],"true":[114],"connection":[115],"discriminative":[117],"labels.":[120],"Extensive":[121],"experiments":[122,141],"clearly":[123],"demonstrate":[124],"effectiveness":[126,155],"our":[128,157],"method":[129,158],"multiple":[131],"generalization":[133,144],"benchmarks":[134,145],"compared":[135,159],"with":[136,160],"state-of-the-art":[137,161],"counterparts.":[138,162],"Through":[139],"extensive":[140],"including":[146],"PACS,":[147],"VLCS,":[148],"MNIST-M,":[149],"NICO,":[151],"show":[153]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":66},{"year":2024,"cited_by_count":83},{"year":2023,"cited_by_count":65},{"year":2022,"cited_by_count":34},{"year":2021,"cited_by_count":5}],"updated_date":"2026-04-07T14:57:38.498316","created_date":"2025-10-10T00:00:00"}
