{"id":"https://openalex.org/W2921871639","doi":"https://doi.org/10.1117/12.2523182","title":"Towards multi-class detection: a self-learning approach to reduce inter-class noise from training dataset","display_name":"Towards multi-class detection: a self-learning approach to reduce inter-class noise from training dataset","publication_year":2019,"publication_date":"2019-03-15","ids":{"openalex":"https://openalex.org/W2921871639","doi":"https://doi.org/10.1117/12.2523182","mag":"2921871639"},"language":"en","primary_location":{"id":"doi:10.1117/12.2523182","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2523182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Eleventh International Conference on Machine Vision (ICMV 2018)","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/A5087485596","display_name":"Amir Ghahremani","orcid":"https://orcid.org/0000-0002-3572-5496"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Amir Ghahremani","raw_affiliation_strings":["Eindhoven Univ. of Technology (Netherlands)"],"affiliations":[{"raw_affiliation_string":"Eindhoven Univ. of Technology (Netherlands)","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069685461","display_name":"Egor Bondarev","orcid":"https://orcid.org/0009-0005-2452-7389"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Egor Bondarev","raw_affiliation_strings":["Eindhoven Univ. of Technology (Netherlands)"],"affiliations":[{"raw_affiliation_string":"Eindhoven Univ. of Technology (Netherlands)","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029008213","display_name":"Peter H. N. de With","orcid":"https://orcid.org/0000-0002-7639-7716"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter H. N. de With","raw_affiliation_strings":["Eindhoven Univ. of Technology (Germany)"],"affiliations":[{"raw_affiliation_string":"Eindhoven Univ. of Technology (Germany)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087485596"],"corresponding_institution_ids":["https://openalex.org/I83019370"],"apc_list":null,"apc_paid":null,"fwci":0.1443,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55402112,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"65","issue":null,"first_page":"104","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9919000267982483,"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":0.9919000267982483,"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":0.9790999889373779,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9667999744415283,"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/class","display_name":"Class (philosophy)","score":0.7362467050552368},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.719589352607727},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6926673650741577},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6841214299201965},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.667639434337616},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5859243869781494},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5074016451835632},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.458763062953949},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4405987858772278},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4203943908214569},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3803994655609131},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.336701363325119}],"concepts":[{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.7362467050552368},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.719589352607727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6926673650741577},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6841214299201965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.667639434337616},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5859243869781494},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5074016451835632},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.458763062953949},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4405987858772278},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4203943908214569},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3803994655609131},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.336701363325119}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1117/12.2523182","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2523182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Eleventh International Conference on Machine Vision (ICMV 2018)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/74d51aa0-3376-44f6-a75b-04ccae5eb065","is_oa":false,"landing_page_url":"https://research.tue.nl/en/publications/74d51aa0-3376-44f6-a75b-04ccae5eb065","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ghahremani, A, Bondarev, E & de With, P H N 2019, Towards multi-class detection : a self-learning approach to reduce inter-class noise from training dataset. in A Verikas, D P Nikolaev, P Radeva & J Zhou (eds), Eleventh International Conference on Machine Vision, ICMV 2018., 110411M, Proceedings of SPIE, vol. 11041, SPIE, 11th International Conference on Machine Vision, ICMV 2018, Munich, Germany, 1/11/18. https://doi.org/10.1117/12.2523182","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:908599","is_oa":false,"landing_page_url":"http://library.tue.nl/csp/dare/LinkToRepository.csp?recordnumber=908599","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:library.tue.nl:908599","is_oa":false,"landing_page_url":"http://repository.tue.nl/908599","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.tue.nl:publications/74d51aa0-3376-44f6-a75b-04ccae5eb065","is_oa":false,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85063474924&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ghahremani, A, Bondarev, E & de With, P H N 2019, Towards multi-class detection : a self-learning approach to reduce inter-class noise from training dataset. in A Verikas, D P Nikolaev, P Radeva & J Zhou (eds), Eleventh International Conference on Machine Vision, ICMV 2018., 110411M, Proceedings of SPIE, vol. 11041, SPIE, 11th International Conference on Machine Vision, ICMV 2018, Munich, Germany, 1/11/18. https://doi.org/10.1117/12.2523182","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:tue:oai:pure.tue.nl:publications/74d51aa0-3376-44f6-a75b-04ccae5eb065","is_oa":false,"landing_page_url":"https://research.tue.nl/nl/publications/74d51aa0-3376-44f6-a75b-04ccae5eb065","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Eleventh International Conference on Machine Vision, ICMV 2018","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","display_name":"Life below water","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1739260168","https://openalex.org/W2032723017","https://openalex.org/W2097117768","https://openalex.org/W2124219775","https://openalex.org/W2125612763","https://openalex.org/W2147483361","https://openalex.org/W2149617813","https://openalex.org/W2261164546","https://openalex.org/W2287418003","https://openalex.org/W2322112093","https://openalex.org/W2550390883","https://openalex.org/W2598915960","https://openalex.org/W2758104367","https://openalex.org/W2794657656","https://openalex.org/W2963028646","https://openalex.org/W3099407522","https://openalex.org/W6637373629","https://openalex.org/W6637774275","https://openalex.org/W6674914833","https://openalex.org/W6678441625","https://openalex.org/W6678660417","https://openalex.org/W6692536993","https://openalex.org/W6696078910","https://openalex.org/W6712300348","https://openalex.org/W6729438419","https://openalex.org/W6729505544","https://openalex.org/W6735151324","https://openalex.org/W6750014702","https://openalex.org/W6784913436"],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W4287027631","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W4390524233"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,9,16,37,67,75,91,108,112,118],"novel":[4],"self-learning":[5],"framework,":[6],"which":[7,34,72,83],"converts":[8],"noisy,":[10],"pre-labeled":[11],"multi-class":[12,18,76,114,122],"object":[13,19,22,70,123],"dataset":[14,20,115,149],"into":[15,139],"purified":[17,113],"with":[21,66,105],"bounding-box":[23],"annotations,":[24],"by":[25,160,198],"iteratively":[26,46],"removing":[27],"noise":[28,42,181,206],"samples":[29,182],"from":[30],"the":[31,48,57,84,102,120,147,152,156,165,168,172,193,201,209],"low-quality":[32],"dataset,":[33],"may":[35],"contain":[36,176],"high":[38,93],"level":[39],"of":[40,82,167,186],"inter-class":[41,180,205],"samples.":[43],"The":[44,63,95,125,143],"framework":[45,97,127,154],"purifies":[47],"noisy":[49],"training":[50,174],"datasets":[51,175],"for":[52,60],"each":[53],"class":[54],"and":[55,116,162,178,188],"updates":[56],"classification":[58],"model":[59,71,77],"multiple":[61],"classes.":[62],"procedure":[64,81],"starts":[65],"generic":[68],"single-class":[69],"changes":[73],"to":[74,89,136],"in":[78],"an":[79],"iterative":[80],"F-1":[85,157],"score":[86,158],"is":[87,98,128],"evaluated":[88,129],"reach":[90],"sufficiently":[92],"score.":[94],"proposed":[96,126,153],"based":[99],"on":[100,130,146],"learning":[101],"used":[103],"models":[104],"CNNs.":[106],"As":[107],"result,":[109],"we":[110],"obtain":[111],"as":[117],"spin-off,":[119],"updated":[121],"model.":[124],"maritime":[131],"surveillance,":[132],"where":[133],"vessels":[134,187],"need":[135],"be":[137],"classified":[138,184],"eight":[140],"different":[141],"types.":[142],"experimental":[144],"results":[145],"evaluation":[148],"show":[150],"that":[151],"improves":[155],"approximately":[159],"5%":[161],"25%":[163],"at":[164],"end":[166],"third":[169],"iteration,":[170],"while":[171,208],"initial":[173],"40%":[177],"60%":[179,204],"(erroneously":[183],"labels":[185],"without":[189],"annotations),":[190],"respectively.":[191],"Additionally,":[192],"recall":[194],"rate":[195,214],"increases":[196],"nearly":[197],"38%":[199],"(for":[200],"more":[202],"challenging":[203],"case),":[207],"mean":[210],"Average":[211],"Precision":[212],"(mAP)":[213],"remains":[215],"stable.":[216]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}