{"id":"https://openalex.org/W7117464922","doi":"https://doi.org/10.1109/dicta68720.2025.11302494","title":"Logit Mixture Outlier Exposure for Fine-Grained Out-Of-Distribution Detection","display_name":"Logit Mixture Outlier Exposure for Fine-Grained Out-Of-Distribution Detection","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7117464922","doi":"https://doi.org/10.1109/dicta68720.2025.11302494"},"language":null,"primary_location":{"id":"doi:10.1109/dicta68720.2025.11302494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta68720.2025.11302494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","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/A5121490049","display_name":"Akito Shinohara","orcid":null},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Akito Shinohara","raw_affiliation_strings":["Hiroshima University,Hiroshima,Japan"],"affiliations":[{"raw_affiliation_string":"Hiroshima University,Hiroshima,Japan","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112178188","display_name":"K Fukuda","orcid":null},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kohei Fukuda","raw_affiliation_strings":["Hiroshima University,Hiroshima,Japan"],"affiliations":[{"raw_affiliation_string":"Hiroshima University,Hiroshima,Japan","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102363518","display_name":"Hiroaki Aizawa","orcid":null},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroaki Aizawa","raw_affiliation_strings":["Hiroshima University,Hiroshima,Japan"],"affiliations":[{"raw_affiliation_string":"Hiroshima University,Hiroshima,Japan","institution_ids":["https://openalex.org/I113306721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5121490049"],"corresponding_institution_ids":["https://openalex.org/I113306721"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84272482,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.8547999858856201,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.8547999858856201,"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":0.026599999517202377,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.019899999722838402,"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/outlier","display_name":"Outlier","score":0.7383999824523926},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5929999947547913},{"id":"https://openalex.org/keywords/logit","display_name":"Logit","score":0.5602999925613403},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4779999852180481},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.4733999967575073},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.41519999504089355},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4106000065803528},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.40610000491142273},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.3644999861717224}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.7383999824523926},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5929999947547913},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.5602999925613403},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5485000014305115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49950000643730164},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4779999852180481},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.4733999967575073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42160001397132874},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.41519999504089355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4106000065803528},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.3644999861717224},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35280001163482666},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.33489999175071716},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.31839999556541443},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.28790000081062317},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26499998569488525},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C2988382989","wikidata":"https://www.wikidata.org/wiki/Q370685","display_name":"Data space","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dicta68720.2025.11302494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta68720.2025.11302494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5866960883140564}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W153185079","https://openalex.org/W1954152232","https://openalex.org/W2992308087","https://openalex.org/W4285606429","https://openalex.org/W4307823382","https://openalex.org/W4319300250"],"related_works":[],"abstract_inverted_index":{"The":[0],"ability":[1],"to":[2,66,74,124,143],"detect":[3],"out-of-distribution":[4,31,45,81,122,133,138,200,214],"data":[5,18,52,76,123,139],"is":[6],"essential":[7],"not":[8],"only":[9],"for":[10,21,64,137],"ensuring":[11],"robustness":[12],"against":[13],"unknown":[14],"or":[15,104],"unexpected":[16],"input":[17,103,168],"but":[19],"also":[20],"improving":[22],"the":[23,27,50,68,87,91,102,115,132,144,152,158,167,179,183,187,205,208],"generalization":[24],"performance":[25,47],"of":[26,207],"model.":[28],"Among":[29],"various":[30],"detection":[32,46,134,215],"methods,":[33],"Outlier":[34,38],"Exposure":[35,39],"and":[36,73,80,121,130,161,193,199],"Mixture":[37],"are":[40,96],"promising":[41],"approaches":[42],"that":[43,118,140,173],"enhance":[44],"by":[48],"exposing":[49],"outlier":[51],"during":[53],"training.":[54],"However,":[55],"even":[56],"with":[57],"these":[58],"sophisticated":[59],"techniques,":[60],"it":[61],"remains":[62],"challenging":[63],"models":[65],"learn":[67],"relationships":[69],"between":[70,93,128,151,197],"classes":[71,129],"effectively":[72],"distinguish":[75],"sampling":[77],"from":[78,99],"in-distribution":[79,120,145,198],"clearly.":[82],"Therefore,":[83],"we":[84,108,148,203],"focus":[85],"on":[86,211],"logit":[88,116,159],"space,":[89],"where":[90],"properties":[92],"class-wise":[94],"distributions":[95],"distinctly":[97],"separated":[98],"those":[100,162],"in":[101,114,157,166,182,191],"feature":[105],"spaces.":[106],"Specifically,":[107],"propose":[109],"a":[110,212],"linear":[111],"interpolation":[112],"technique":[113,177],"space":[117,160],"mixes":[119],"facilitate":[125],"smoothing":[126],"logits":[127,153],"improve":[131],"performance,":[135],"particularly":[136],"lie":[141],"close":[142],"data.":[146,201],"Additionally,":[147],"enforce":[149],"consistency":[150],"obtained":[154],"through":[155],"mixing":[156,165,176],"generated":[163],"via":[164],"space.":[169],"Our":[170],"experiments":[171],"demonstrate":[172],"our":[174],"logit-space":[175],"reduces":[178],"abrupt":[180],"fluctuations":[181],"model":[184],"outputs":[185],"near":[186],"decision":[188],"boundaries,":[189],"resulting":[190],"smoother":[192],"more":[194],"reliable":[195],"separation":[196],"Furthermore,":[202],"evaluate":[204],"effectiveness":[206],"proposed":[209],"method":[210],"fine-grained":[213],"task.":[216]},"counts_by_year":[],"updated_date":"2025-12-30T23:08:21.542490","created_date":"2025-12-29T00:00:00"}