{"id":"https://openalex.org/W3082232744","doi":"https://doi.org/10.1145/3411408.3411441","title":"Combining PENCIL with AMDIM for image classification with noisy and sparsely labeled data","display_name":"Combining PENCIL with AMDIM for image classification with noisy and sparsely labeled data","publication_year":2020,"publication_date":"2020-09-01","ids":{"openalex":"https://openalex.org/W3082232744","doi":"https://doi.org/10.1145/3411408.3411441","mag":"3082232744"},"language":"en","primary_location":{"id":"doi:10.1145/3411408.3411441","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3411408.3411441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th Hellenic Conference on Artificial Intelligence","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/A5072226600","display_name":"Alexandros Petropoulos","orcid":"https://orcid.org/0000-0001-7570-6532"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Alexandros Petropoulos","raw_affiliation_strings":["Aristotle University of Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Aristotle University of Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004953619","display_name":"Christos Diou","orcid":"https://orcid.org/0000-0002-2461-1928"},"institutions":[{"id":"https://openalex.org/I32762134","display_name":"Harokopio University of Athens","ror":"https://ror.org/02k5gp281","country_code":"GR","type":"education","lineage":["https://openalex.org/I32762134"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Christos Diou","raw_affiliation_strings":["Harokopio University of Athens, Greece"],"affiliations":[{"raw_affiliation_string":"Harokopio University of Athens, Greece","institution_ids":["https://openalex.org/I32762134"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5072226600"],"corresponding_institution_ids":["https://openalex.org/I21370196"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09984331,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"93","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9998999834060669,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9998999834060669,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9954000115394592,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9939000010490417,"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/computer-science","display_name":"Computer science","score":0.773224413394928},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.6964940428733826},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.6883438229560852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6740498542785645},{"id":"https://openalex.org/keywords/pencil","display_name":"Pencil (optics)","score":0.6546916961669922},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.579893946647644},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5575799345970154},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5405648350715637},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.521118700504303},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4380124807357788},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.43677735328674316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.773224413394928},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.6964940428733826},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.6883438229560852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6740498542785645},{"id":"https://openalex.org/C134949993","wikidata":"https://www.wikidata.org/wiki/Q2068617","display_name":"Pencil (optics)","level":2,"score":0.6546916961669922},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.579893946647644},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5575799345970154},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5405648350715637},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.521118700504303},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4380124807357788},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.43677735328674316},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3411408.3411441","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3411408.3411441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th Hellenic Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2031494935","https://openalex.org/W2106050175","https://openalex.org/W2114296497","https://openalex.org/W2167460663","https://openalex.org/W2239739895","https://openalex.org/W2471768434","https://openalex.org/W2577784528","https://openalex.org/W2769515224","https://openalex.org/W2842511635","https://openalex.org/W2944828972","https://openalex.org/W2948012107","https://openalex.org/W2949427019","https://openalex.org/W2962843773","https://openalex.org/W2964274690","https://openalex.org/W2967052791","https://openalex.org/W2984353870","https://openalex.org/W2996060033","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W2130553454","https://openalex.org/W3022007134","https://openalex.org/W4317548404","https://openalex.org/W1509924131","https://openalex.org/W160673860","https://openalex.org/W3104108945","https://openalex.org/W2033364610","https://openalex.org/W4289766121","https://openalex.org/W3163689946","https://openalex.org/W4308757581"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2,39],"seen":[3],"an":[4],"increase":[5],"in":[6,18],"data":[7,93],"availability":[8],"and":[9,66,85,111],"computational":[10],"power,":[11],"which":[12],"has":[13],"led":[14],"to":[15,115],"superior":[16],"performance":[17,60],"training":[19,32,84],"deep":[20],"learning":[21,91],"models":[22],"for":[23,43,57,79,90],"image":[24],"classification.":[25],"In":[26,51,68],"many":[27],"real-world":[28],"use-cases,":[29],"however,":[30],"the":[31,48,62,72],"datasets":[33],"come":[34],"with":[35,109],"noisy":[36,65,81,112],"labels":[37,63,82],"that":[38,100],"been":[40],"automatically":[41],"generated":[42],"a":[44,77,87],"small":[45],"subset":[46],"of":[47,74,118],"available":[49],"data.":[50,97],"this":[52,101],"paper":[53],"we":[54,70],"explore":[55],"strategies":[56],"maintaining":[58],"classification":[59],"when":[61,107],"become":[64],"sparse.":[67],"particular,":[69],"evaluate":[71],"effectiveness":[73],"combining":[75],"PENCIL,":[76],"framework":[78],"correcting":[80],"during":[83],"AMDIM,":[86],"self-supervised":[88],"technique":[89],"good":[92],"representations":[94],"from":[95],"unlabeled":[96],"We":[98],"find":[99],"combination":[102],"is":[103],"significantly":[104],"more":[105],"effective":[106],"dealing":[108],"sparse":[110],"labels,":[113],"compared":[114],"using":[116],"either":[117],"these":[119],"approaches":[120],"alone.":[121]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}