{"id":"https://openalex.org/W4304084228","doi":"https://doi.org/10.1145/3503161.3548289","title":"Angular Gap: Reducing the Uncertainty of Image Difficulty through Model Calibration","display_name":"Angular Gap: Reducing the Uncertainty of Image Difficulty through Model Calibration","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304084228","doi":"https://doi.org/10.1145/3503161.3548289"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548289","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548289","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://discovery.ucl.ac.uk/10161581/1/2207.08525.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101503808","display_name":"Bohua Peng","orcid":"https://orcid.org/0000-0001-8037-6072"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Bohua Peng","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066653567","display_name":"Mobarakol Islam","orcid":"https://orcid.org/0000-0002-7162-2822"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mobarakol Islam","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108647194","display_name":"Mei Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mei Tu","raw_affiliation_strings":["Samsung Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Samsung Research, Beijing, China","institution_ids":["https://openalex.org/I4210155230"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101503808"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.9394,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.76901468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"979","last_page":"987"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9884999990463257,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9884999990463257,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9846000075340271,"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"}},{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9747999906539917,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6804963946342468},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.6350151300430298},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5846234560012817},{"id":"https://openalex.org/keywords/credibility","display_name":"Credibility","score":0.5820184946060181},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5270866751670837},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5080184936523438},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.4703255891799927},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4536955654621124},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.43476149439811707},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4333111345767975},{"id":"https://openalex.org/keywords/angular-velocity","display_name":"Angular velocity","score":0.419176310300827},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19596463441848755},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11375859379768372},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08268117904663086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6804963946342468},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6350151300430298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5846234560012817},{"id":"https://openalex.org/C2780224610","wikidata":"https://www.wikidata.org/wiki/Q1530061","display_name":"Credibility","level":2,"score":0.5820184946060181},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5270866751670837},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5080184936523438},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.4703255891799927},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4536955654621124},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43476149439811707},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4333111345767975},{"id":"https://openalex.org/C5594486","wikidata":"https://www.wikidata.org/wiki/Q161635","display_name":"Angular velocity","level":2,"score":0.419176310300827},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19596463441848755},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11375859379768372},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08268117904663086},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3503161.3548289","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548289","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10161581","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10161581/","pdf_url":"https://discovery.ucl.ac.uk/10161581/1/2207.08525.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In:  Proceedings of the 30th ACM International Conference on Multimedia.  (pp. pp. 979-987).  ACM (2022)     ","raw_type":"Proceedings paper"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/1042757e-27f9-4117-8a7d-ac5aa1cb7023","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/1042757e-27f9-4117-8a7d-ac5aa1cb7023","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Peng, B, Islam, M & Tu, M 2022, 'Angular Gap: Reducing the Uncertainty of Image Difficulty through Model Calibration', arXiv.","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10161581","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10161581/","pdf_url":"https://discovery.ucl.ac.uk/10161581/1/2207.08525.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In:  Proceedings of the 30th ACM International Conference on Multimedia.  (pp. pp. 979-987).  ACM (2022)     ","raw_type":"Proceedings paper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8500000238418579,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4304084228.pdf"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2548695521","https://openalex.org/W2739759330","https://openalex.org/W2895281799","https://openalex.org/W2904549000","https://openalex.org/W2942457804","https://openalex.org/W2962898354","https://openalex.org/W2963168418","https://openalex.org/W2969985801","https://openalex.org/W2985406498","https://openalex.org/W3001197829","https://openalex.org/W3021632667","https://openalex.org/W3095155674","https://openalex.org/W3101281919","https://openalex.org/W3176602994"],"related_works":["https://openalex.org/W2388687352","https://openalex.org/W2370187191","https://openalex.org/W1990162851","https://openalex.org/W2369854048","https://openalex.org/W2374291020","https://openalex.org/W2355907197","https://openalex.org/W3171042291","https://openalex.org/W2390961115","https://openalex.org/W2136627352","https://openalex.org/W2368237856"],"abstract_inverted_index":{"Curriculum":[0],"learning":[1,123],"needs":[2],"example":[3],"difficulty":[4,16,38,58,100],"to":[5,9,69,126],"proceed":[6],"from":[7,122],"easy":[8,124],"hard.":[10],"However,":[11],"the":[12,24,41,70,76,91],"credibility":[13],"of":[14,26,37,86,93],"image":[15],"is":[17],"rarely":[18],"investigated,":[19],"which":[20],"can":[21,120],"seriously":[22],"affect":[23],"effectiveness":[25],"curricula.":[27],"In":[28],"this":[29,132],"work,":[30],"we":[31,60],"propose":[32,108],"Angular":[33,96,113],"Gap,":[34],"a":[35,66,109,135],"measure":[36],"based":[39,111],"on":[40,102,112,154],"difference":[42],"in":[43],"angular":[44,83],"distance":[45,84],"between":[46,78],"feature":[47],"embeddings":[48,51],"and":[49,82,104,150,156],"class-weight":[50],"built":[52],"by":[53],"hyperspherical":[54,87],"learning.":[55,88],"To":[56],"ascertain":[57],"estimation,":[59],"introduce":[61],"class-wise":[62],"model":[63,80],"calibration,":[64],"as":[65],"post-training":[67],"technique,":[68],"learnt":[71],"hyperbolic":[72],"space.":[73],"This":[74],"bridges":[75],"gap":[77],"probabilistic":[79],"calibration":[81],"estimation":[85],"We":[89,106,130],"show":[90],"superiority":[92],"our":[94],"calibrated":[95],"Gap":[97,114],"over":[98],"recent":[99,152],"metrics":[101],"CIFAR10-H":[103],"ImageNetV2.":[105],"further":[107],"curriculum":[110,133],"for":[115],"unsupervised":[116],"domain":[117],"adaptation":[118],"that":[119],"translate":[121],"samples":[125],"mining":[127],"hard":[128],"samples.":[129],"combine":[131],"with":[134],"state-of-the-art":[136],"self-training":[137],"method,":[138],"Cycle":[139],"Self":[140],"Training":[141],"(CST).":[142],"The":[143],"proposed":[144],"Curricular":[145],"CST":[146],"learns":[147],"robust":[148],"representations":[149],"outperforms":[151],"baselines":[153],"Office31":[155],"VisDA":[157],"2017.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}