{"id":"https://openalex.org/W4308236844","doi":"https://doi.org/10.1109/icip46576.2022.9897514","title":"Forgetful Active Learning with Switch Events: Efficient Sampling for Out-of-Distribution Data","display_name":"Forgetful Active Learning with Switch Events: Efficient Sampling for Out-of-Distribution Data","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308236844","doi":"https://doi.org/10.1109/icip46576.2022.9897514"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897514","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2301.05106","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085156570","display_name":"Ryan Benkert","orcid":"https://orcid.org/0000-0002-9634-9359"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ryan Benkert","raw_affiliation_strings":["Georgia Institute of Technology,OLIVES at the Center for Signal and Information Processing, School of Electrical and Computer Engineering,Atlanta,GA,USA,30332-0250"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,OLIVES at the Center for Signal and Information Processing, School of Electrical and Computer Engineering,Atlanta,GA,USA,30332-0250","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010958338","display_name":"Mohit Prabhushankar","orcid":"https://orcid.org/0000-0002-8743-7058"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohit Prabhushankar","raw_affiliation_strings":["Georgia Institute of Technology,OLIVES at the Center for Signal and Information Processing, School of Electrical and Computer Engineering,Atlanta,GA,USA,30332-0250"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,OLIVES at the Center for Signal and Information Processing, School of Electrical and Computer Engineering,Atlanta,GA,USA,30332-0250","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006145139","display_name":"Ghassan AlRegib","orcid":"https://orcid.org/0000-0001-6818-8001"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ghassan AlRegib","raw_affiliation_strings":["Georgia Institute of Technology,OLIVES at the Center for Signal and Information Processing, School of Electrical and Computer Engineering,Atlanta,GA,USA,30332-0250"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,OLIVES at the Center for Signal and Information Processing, School of Electrical and Computer Engineering,Atlanta,GA,USA,30332-0250","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085156570"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.733,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.71850321,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"34","issue":null,"first_page":"2196","last_page":"2200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9998000264167786,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9998000264167786,"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":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9955000281333923,"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":0.7547882795333862},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6515897512435913},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6465035676956177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6315783262252808},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6231818199157715},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.5860759615898132},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5284818410873413},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4924374520778656},{"id":"https://openalex.org/keywords/external-data-representation","display_name":"External Data Representation","score":0.44225257635116577},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.43561264872550964},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.43166327476501465},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37156790494918823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7547882795333862},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6515897512435913},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6465035676956177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6315783262252808},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6231818199157715},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.5860759615898132},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5284818410873413},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4924374520778656},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.44225257635116577},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.43561264872550964},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.43166327476501465},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37156790494918823},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icip46576.2022.9897514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897514","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2301.05106","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.05106","pdf_url":"https://arxiv.org/pdf/2301.05106","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2301.05106","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.05106","pdf_url":"https://arxiv.org/pdf/2301.05106","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4308236844.pdf"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W603830301","https://openalex.org/W1872312298","https://openalex.org/W2011674654","https://openalex.org/W2560647685","https://openalex.org/W2774918944","https://openalex.org/W2803552920","https://openalex.org/W2911333381","https://openalex.org/W2948367246","https://openalex.org/W2949071206","https://openalex.org/W2951013084","https://openalex.org/W2980692935","https://openalex.org/W3090434739","https://openalex.org/W3091094992","https://openalex.org/W3091518487","https://openalex.org/W3110039477","https://openalex.org/W3137603776","https://openalex.org/W3180672483","https://openalex.org/W3195386208","https://openalex.org/W3195951188","https://openalex.org/W4288404646","https://openalex.org/W4297745950","https://openalex.org/W4394639701","https://openalex.org/W6639393196","https://openalex.org/W6747231328","https://openalex.org/W6747438826","https://openalex.org/W6752540598","https://openalex.org/W6755174528","https://openalex.org/W6757248479","https://openalex.org/W6757555829","https://openalex.org/W6758759751","https://openalex.org/W6763607942","https://openalex.org/W6769142653","https://openalex.org/W6791836043","https://openalex.org/W6798999318"],"related_works":["https://openalex.org/W2056314584","https://openalex.org/W1492505081","https://openalex.org/W1986633584","https://openalex.org/W2976807053","https://openalex.org/W184546935","https://openalex.org/W2909115059","https://openalex.org/W2908248196","https://openalex.org/W2943886396","https://openalex.org/W2515319207","https://openalex.org/W4224292393"],"abstract_inverted_index":{"This":[0],"paper":[1],"considers":[2],"deep":[3],"out-of-distribution":[4,16,123],"active":[5,54,110,119,124],"learning.":[6,125],"In":[7],"practice,":[8],"fully":[9],"trained":[10],"neural":[11],"networks":[12],"interact":[13],"randomly":[14,23],"with":[15,112,139],"(OOD)":[17],"inputs":[18],"and":[19,154,184],"map":[20],"aberrant":[21],"samples":[22,101,153,159],"within":[24],"the":[25,36,39,68,85,89,93,132,149,156],"model":[26],"representation":[27,78,91,134],"space.":[28,79],"Since":[29],"data":[30,40,86,90,95,133],"representations":[31],"are":[32],"direct":[33],"manifestations":[34],"of":[35,92,127],"training":[37,69],"distribution,":[38],"selection":[41,87],"process":[42],"plays":[43],"a":[44,76,117],"crucial":[45],"role":[46],"in":[47,169],"outlier":[48],"robustness.":[49],"For":[50,104],"paradigms":[51],"such":[52],"as":[53],"learning,":[55],"this":[56,105],"is":[57,97],"especially":[58],"challenging":[59],"since":[60],"protocols":[61],"must":[62],"not":[63],"only":[64],"improve":[65],"performance":[66],"on":[67,88,131],"distribution":[70],"most":[71,157],"effectively":[72],"but":[73],"further":[74],"render":[75],"robust":[77],"However,":[80],"existing":[81],"strategies":[82],"directly":[83],"base":[84],"unlabeled":[94,152],"which":[96],"random":[98],"for":[99,122,160],"OOD":[100,179],"by":[102],"definition.":[103],"purpose,":[106],"we":[107,136,145],"introduce":[108],"forgetful":[109],"learning":[111,120,140],"switch":[113],"events":[114],"(FALSE)":[115],"-":[116],"novel":[118],"protocol":[121],"Instead":[126],"defining":[128],"sample":[129],"importance":[130],"directly,":[135],"formulate":[137],"\"informativeness\"":[138],"difficulty":[141],"during":[142],"training.":[143],"Specifically,":[144],"approximate":[146],"how":[147],"often":[148],"network":[150],"\"forgets\"":[151],"query":[155],"\"forgotten\"":[158],"annotation.":[161],"We":[162],"report":[163],"up":[164],"to":[165],"4.5%":[166],"accuracy":[167],"improvements":[168],"over":[170],"270":[171],"experiments,":[172],"including":[173],"four":[174],"commonly":[175],"used":[176],"protocols,":[177],"two":[178],"benchmarks,":[180],"one":[181],"in-distribution":[182],"benchmark,":[183],"three":[185],"different":[186],"architectures.":[187]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}