{"id":"https://openalex.org/W3158533370","doi":"https://doi.org/10.1109/icpr48806.2021.9412612","title":"Boundary Optimised Samples Training for Detecting Out-of-Distribution Images","display_name":"Boundary Optimised Samples Training for Detecting Out-of-Distribution Images","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3158533370","doi":"https://doi.org/10.1109/icpr48806.2021.9412612","mag":"3158533370"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th 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/A5009261369","display_name":"Luca Marson","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Luca Marson","raw_affiliation_strings":["Nordetect ApS"],"affiliations":[{"raw_affiliation_string":"Nordetect ApS","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012030843","display_name":"Vladimir Li","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Vladimir Li","raw_affiliation_strings":["Division of Robotics, Perception, and Learning, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Division of Robotics, Perception, and Learning, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054834085","display_name":"Atsuto Maki","orcid":"https://orcid.org/0000-0002-4266-6746"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Atsuto Maki","raw_affiliation_strings":["Division of Robotics, Perception, and Learning, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Division of Robotics, Perception, and Learning, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009261369"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51906424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"80","issue":null,"first_page":"10486","last_page":"10492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9987999796867371,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9907000064849854,"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/softmax-function","display_name":"Softmax function","score":0.8573309779167175},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7901513576507568},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7007676362991333},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.6836295127868652},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6020529270172119},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5654374361038208},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.535304844379425},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4633878171443939},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.45674198865890503},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42605456709861755},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3270435929298401},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.29886913299560547},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.23986729979515076},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19830632209777832}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8573309779167175},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7901513576507568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7007676362991333},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.6836295127868652},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6020529270172119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5654374361038208},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.535304844379425},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4633878171443939},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.45674198865890503},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42605456709861755},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3270435929298401},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.29886913299560547},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.23986729979515076},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19830632209777832},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"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/icpr48806.2021.9412612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322509","display_name":"Kungliga Tekniska H\u00f6gskolan","ror":"https://ror.org/026vcq606"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1480538416","https://openalex.org/W1686810756","https://openalex.org/W1710476689","https://openalex.org/W1825675169","https://openalex.org/W2095705004","https://openalex.org/W2335728318","https://openalex.org/W2340896621","https://openalex.org/W2460937040","https://openalex.org/W2531327146","https://openalex.org/W2618169590","https://openalex.org/W2734358244","https://openalex.org/W2750384547","https://openalex.org/W2767414122","https://openalex.org/W2770833542","https://openalex.org/W2789159078","https://openalex.org/W2803697594","https://openalex.org/W2904981516","https://openalex.org/W2951883849","https://openalex.org/W2962835968","https://openalex.org/W2963149653","https://openalex.org/W2963238274","https://openalex.org/W2963384319","https://openalex.org/W2963546708","https://openalex.org/W2963613748","https://openalex.org/W2963995504","https://openalex.org/W2964253222","https://openalex.org/W2978074392","https://openalex.org/W3118608800","https://openalex.org/W4293321333","https://openalex.org/W4293846201","https://openalex.org/W4298289240","https://openalex.org/W4300511536","https://openalex.org/W6628642759","https://openalex.org/W6637373629","https://openalex.org/W6674330103","https://openalex.org/W6703116779","https://openalex.org/W6728622933","https://openalex.org/W6730042731","https://openalex.org/W6738348428","https://openalex.org/W6739868092","https://openalex.org/W6745553787","https://openalex.org/W6745891213","https://openalex.org/W6746424632","https://openalex.org/W6748366383","https://openalex.org/W6751494907","https://openalex.org/W6755655770","https://openalex.org/W6757615711"],"related_works":["https://openalex.org/W2950475743","https://openalex.org/W4386603768","https://openalex.org/W2886711096","https://openalex.org/W4380078352","https://openalex.org/W3046591097","https://openalex.org/W2590796488","https://openalex.org/W2771907641","https://openalex.org/W4283819496","https://openalex.org/W4381430104","https://openalex.org/W3194633786"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,103,129,174],"new":[4,184],"approach":[5],"to":[6,26,83,109,124,133],"the":[7,38,45,69,75,84,88,91,95,110,117,148,152,183],"problem":[8],"of":[9,77,90],"detecting":[10],"out-of-distribution":[11],"(OOD)":[12],"inputs":[13,34],"in":[14,99],"image":[15],"classifications":[16],"with":[17,107,173],"deep":[18],"convolutional":[19],"networks.":[20],"We":[21,150],"leverage":[22],"so-called":[23],"boundary":[24,46,96,126],"samples":[25,48,97],"enforce":[27,134],"low":[28,135],"confidence":[29,136],"(maximum":[30],"softmax":[31],"probabilities)":[32],"for":[33,53,137,157,182],"far":[35],"away":[36],"from":[37],"training":[39,51,119,158],"data.":[40],"In":[41],"particular,":[42],"we":[43],"propose":[44],"optimised":[47],"(named":[49],"BoS)":[50],"algorithm":[52,131],"generating":[54],"them.":[55],"Unlike":[56],"existing":[57],"approaches,":[58],"it":[59],"does":[60],"not":[61],"require":[62],"extra":[63],"generative":[64],"adversarial":[65],"network,":[66],"but":[67],"achieves":[68],"goal":[70],"by":[71,171],"simply":[72],"back":[73],"propagating":[74],"gradient":[76],"an":[78,121,180],"appropriately":[79],"designed":[80,111],"loss":[81],"function":[82],"input":[85],"samples.":[86],"At":[87],"end":[89],"BoS":[92,118],"training,":[93],"all":[94],"are":[98,115],"principle":[100],"located":[101],"on":[102],"specific":[104],"level":[105],"hypersurface":[106],"respect":[108],"loss.":[112],"Our":[113],"contributions":[114],"i)":[116],"as":[120],"efficient":[122],"alternative":[123],"generate":[125],"samples,":[127,139],"ii)":[128],"robust":[130],"therewith":[132],"OOD":[138,145],"and":[140,159,168],"iii)":[141],"experiments":[142],"demonstrating":[143],"improved":[144],"detection":[146],"over":[147],"baseline.":[149],"show":[151],"performance":[153],"using":[154],"standard":[155],"datasets":[156],"different":[160],"test":[161],"sets":[162],"including":[163],"Fashion":[164],"MNIST,":[165],"EMNIST,":[166],"SVHN,":[167],"CIFAR-100,":[169],"preceded":[170],"evaluations":[172],"synthetic":[175],"2-dimensional":[176],"dataset":[177],"that":[178],"provide":[179],"insight":[181],"procedure.":[185]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}