{"id":"https://openalex.org/W4313590636","doi":"https://doi.org/10.1145/3578935","title":"MixOOD: Improving Out-of-distribution Detection with Enhanced Data Mixup","display_name":"MixOOD: Improving Out-of-distribution Detection with Enhanced Data Mixup","publication_year":2022,"publication_date":"2022-09-30","ids":{"openalex":"https://openalex.org/W4313590636","doi":"https://doi.org/10.1145/3578935"},"language":"en","primary_location":{"id":"doi:10.1145/3578935","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3578935","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3578935","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3578935","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040073732","display_name":"Taocun Yang","orcid":"https://orcid.org/0000-0003-3599-9961"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Taocun Yang","raw_affiliation_strings":["Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University, Haidian, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3599-9961","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University, Haidian, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005101751","display_name":"Yaping Huang","orcid":"https://orcid.org/0000-0002-4465-372X"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaping Huang","raw_affiliation_strings":["Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University, Haidian, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4465-372X","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University, Haidian, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062246851","display_name":"Yanlin Xie","orcid":"https://orcid.org/0000-0002-4592-5387"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanlin Xie","raw_affiliation_strings":["School of Computer and Information Technology, Beijing Jiaotong University, Haidian, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4592-5387","affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology, Beijing Jiaotong University, Haidian, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101950365","display_name":"Junbo Liu","orcid":"https://orcid.org/0000-0003-1782-1051"},"institutions":[{"id":"https://openalex.org/I4210141966","display_name":"China Academy of Railway Sciences","ror":"https://ror.org/051wv2j09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210141966"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junbo Liu","raw_affiliation_strings":["Infrastructure Inspection Research Institute, China Academy of Railway Science Corporation Limited, Haidian, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1782-1051","affiliations":[{"raw_affiliation_string":"Infrastructure Inspection Research Institute, China Academy of Railway Science Corporation Limited, Haidian, Beijing, China","institution_ids":["https://openalex.org/I4210141966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101562421","display_name":"Shengchun Wang","orcid":"https://orcid.org/0000-0003-0003-1002"},"institutions":[{"id":"https://openalex.org/I4210141966","display_name":"China Academy of Railway Sciences","ror":"https://ror.org/051wv2j09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210141966"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengchun Wang","raw_affiliation_strings":["Infrastructure Inspection Research Institute, China Academy of Railway Science Corporation Limited, Haidian, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0003-1002","affiliations":[{"raw_affiliation_string":"Infrastructure Inspection Research Institute, China Academy of Railway Science Corporation Limited, Haidian, Beijing, China","institution_ids":["https://openalex.org/I4210141966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5040073732"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.5102,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.65336695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"19","issue":"5","first_page":"1","last_page":"18"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994999766349792,"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":0.9984999895095825,"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/softmax-function","display_name":"Softmax function","score":0.8222342729568481},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6873107552528381},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6824371218681335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5890486240386963},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5022017955780029},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.47187820076942444},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4522087275981903},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4369601011276245},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40105104446411133},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3967534005641937}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8222342729568481},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6873107552528381},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6824371218681335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5890486240386963},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5022017955780029},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47187820076942444},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4522087275981903},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4369601011276245},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40105104446411133},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3967534005641937},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3578935","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3578935","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3578935","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3578935","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3578935","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3578935","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G6294615064","display_name":null,"funder_award_id":"2019JBZ104","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7433449240","display_name":null,"funder_award_id":"62271042, 62106017, 61906013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4313590636.pdf","grobid_xml":"https://content.openalex.org/works/W4313590636.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1954152232","https://openalex.org/W2047643928","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2138011018","https://openalex.org/W2146502635","https://openalex.org/W2161914416","https://openalex.org/W2163605009","https://openalex.org/W2335728318","https://openalex.org/W2531327146","https://openalex.org/W2551176409","https://openalex.org/W2885613075","https://openalex.org/W2889326414","https://openalex.org/W2889625178","https://openalex.org/W2951883849","https://openalex.org/W2954996726","https://openalex.org/W2963446712","https://openalex.org/W2964137095","https://openalex.org/W2992308087","https://openalex.org/W2997167991","https://openalex.org/W3092527263","https://openalex.org/W3118608800","https://openalex.org/W3134961575","https://openalex.org/W3209691732","https://openalex.org/W4283782831","https://openalex.org/W4283796325","https://openalex.org/W4307823382","https://openalex.org/W6683825394","https://openalex.org/W6757615711","https://openalex.org/W6784323503"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W4226420367","https://openalex.org/W2980176872","https://openalex.org/W2962876041","https://openalex.org/W3090555870","https://openalex.org/W3108503355","https://openalex.org/W3170224572","https://openalex.org/W4389120483","https://openalex.org/W3092431721"],"abstract_inverted_index":{"Detecting":[0],"out-of-distribution":[1,201],"(OOD)":[2],"inputs":[3],"for":[4,102,142,187],"deep":[5],"learning":[6],"models":[7,13,193],"is":[8,42,105],"a":[9,20],"critical":[10],"task":[11],"when":[12],"are":[14,77],"deployed":[15],"in":[16,50],"real-world":[17],"environments.":[18],"Recently,":[19],"large":[21],"number":[22],"of":[23,35,207],"works":[24],"have":[25],"been":[26],"dedicated":[27],"to":[28,74,79,87,107,130,164],"tackling":[29],"the":[30,36,51,55,85,138,166,204],"OOD":[31,43,75,92,96,112,122,133,162,167,175],"detection":[32,124],"problem.":[33],"One":[34],"most":[37],"straightforward":[38],"and":[39,65,156,184,200],"effective":[40],"ways":[41],"training,":[44],"which":[45,82],"adds":[46],"heterogeneous":[47],"auxiliary":[48,57,67,161],"data":[49,58,144,163],"training":[52],"stage.":[53],"However,":[54],"extra":[56],"cannot":[59],"be":[60,128],"involved":[61],"arbitrarily.":[62],"A":[63],"high-quality":[64],"powerful":[66],"dataset":[68],"must":[69],"contain":[70],"samples":[71,202],"that":[72,126,192],"belong":[73],"but":[76],"close":[78],"in-distribution":[80],"(ID),":[81],"can":[83,127,196],"teach":[84],"model":[86],"learn":[88],"more":[89],"information":[90],"about":[91],"samples,":[93],"furthermore,":[94],"distinguish":[95,198],"from":[97,137],"ID.":[98],"The":[99],"key":[100],"issue":[101],"this":[103,115],"problem":[104],"how":[106],"simply":[108],"acquire":[109],"such":[110],"distinctive":[111],"samples.":[113],"In":[114],"article,":[116],"we":[117],"propose":[118],"an":[119],"enhanced":[120],"Mixup-based":[121],"(MixOOD)":[123],"strategy":[125],"attached":[129],"any":[131],"threshold-based":[132],"detecting":[134,176],"method.":[135],"Different":[136],"traditional":[139],"Mixup":[140,155],"designed":[141],"ID":[143],"augmentation,":[145],"our":[146,171],"proposed":[147],"MixOOD":[148,195],"generates":[149],"augmented":[150],"images":[151],"with":[152,173,194],"deliberately":[153],"modified":[154],"then":[157],"uses":[158],"them":[159],"as":[160],"leverage":[165],"detection.":[168],"We":[169],"test":[170],"method":[172],"classical":[174],"approaches":[177],"like":[178],"Maximum":[179],"Softmax":[180],"Probability,":[181],"Energy":[182],"Score,":[183],"Out-of-distribution":[185],"detector":[186],"Neural":[188],"networks.":[189],"Experiments":[190],"show":[191],"better":[197],"in-":[199],"than":[203],"original":[205],"version":[206],"each":[208],"approach.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}