{"id":"https://openalex.org/W4386907024","doi":"https://doi.org/10.48550/arxiv.2309.09982","title":"Introspective Deep Metric Learning","display_name":"Introspective Deep Metric Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386907024","doi":"https://doi.org/10.48550/arxiv.2309.09982"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2309.09982","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"posted-content","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/2309.09982","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101468529","display_name":"Chengkun Wang","orcid":"https://orcid.org/0009-0005-4051-4975"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chengkun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006396086","display_name":"Wenzhao Zheng","orcid":"https://orcid.org/0000-0001-7188-3734"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Wenzhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101705530","display_name":"Zheng Zhu","orcid":"https://orcid.org/0000-0002-4435-1692"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Zheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620306","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0001-7701-234X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Jie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100460385","display_name":"Jiwen Lu","orcid":"https://orcid.org/0000-0002-6121-5529"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Jiwen","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":65},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9793,"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"}},"topics":[{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9793,"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/T11448","display_name":"Face recognition and analysis","score":0.9706,"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":0.9536,"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/discriminative-model","display_name":"Discriminative model","score":0.5391441},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47403717}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.72764975},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.66005766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.65906024},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6138143},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5761461},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.56224644},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5391441},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.53170496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.52875465},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49138537},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47403717},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4066238},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33814973},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2309.09982","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.2309.09982","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2309.09982","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.76}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W4205463238","https://openalex.org/W3103844505","https://openalex.org/W2923538289","https://openalex.org/W259157601","https://openalex.org/W2353179089","https://openalex.org/W2353125546","https://openalex.org/W2153315159","https://openalex.org/W2110523656","https://openalex.org/W1482209366"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3,107,117,129,135,168,217],"introspective":[4,136],"deep":[5,16,188],"metric":[6,17,138,158,189],"learning":[7,18,22,190],"(IDML)":[8],"framework":[9,183,222],"for":[10,96,209],"uncertainty-aware":[11],"comparisons":[12],"of":[13,31,37,51,87,128,155,187,220,229],"images.":[14],"Conventional":[15],"methods":[19],"focus":[20],"on":[21,198],"a":[23,76,112],"discriminative":[24],"embedding":[25,114],"to":[26,57,90,105,139,165,173,223],"describe":[27],"the":[28,35,55,59,82,88,123,156,163,176,185,199,225],"semantic":[29,46,83,113,124,148],"features":[30],"images,":[32],"which":[33,121],"ignore":[34],"existence":[36],"uncertainty":[38,89,119,177,192],"in":[39],"each":[40],"image":[41,108,210],"resulting":[42],"from":[43],"noise":[44],"or":[45],"ambiguity.":[47],"Training":[48],"without":[49],"awareness":[50,86],"these":[52],"uncertainties":[53],"causes":[54],"model":[56,79,164],"overfit":[58],"annotated":[60],"labels":[61],"during":[62,68,178],"training":[63],"and":[64,126,150,170,194,204,212,227],"produce":[65],"unsatisfactory":[66],"judgments":[67,142],"inference.":[69],"Motivated":[70],"by":[71],"this,":[72,102],"we":[73,103],"argue":[74],"that":[75,160],"good":[77],"similarity":[78,137,141],"should":[80],"consider":[81],"discrepancies":[84],"with":[85,93,175],"better":[91],"deal":[92,174],"ambiguous":[94],"images":[95,144],"more":[97],"robust":[98],"training.":[99,179],"To":[100],"achieve":[101],"propose":[104,134],"represent":[106],"using":[109],"not":[110],"only":[111],"but":[115],"also":[116],"accompanying":[118],"embedding,":[120],"describes":[122],"characteristics":[125],"ambiguity":[127],"image,":[130],"respectively.":[131],"We":[132,214],"further":[133,215],"make":[140],"between":[143],"considering":[145],"both":[146],"their":[147],"differences":[149],"ambiguities.":[151],"The":[152,180],"gradient":[153],"analysis":[154,219],"proposed":[157,181],"shows":[159],"it":[161],"enables":[162],"learn":[166],"at":[167],"adaptive":[169],"slower":[171],"pace":[172],"IDML":[182],"improves":[184],"performance":[186],"through":[191],"modeling":[193],"attains":[195],"state-of-the-art":[196],"results":[197],"widely":[200],"used":[201],"CUB-200-2011,":[202],"Cars196,":[203],"Stanford":[205],"Online":[206],"Products":[207],"datasets":[208],"retrieval":[211],"clustering.":[213],"provide":[216],"in-depth":[218],"our":[221],"demonstrate":[224],"effectiveness":[226],"reliability":[228],"IDML.":[230],"Code:":[231],"https://github.com/wzzheng/IDML.":[232]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4386907024","counts_by_year":[],"updated_date":"2025-04-08T23:35:27.742510","created_date":"2023-09-21"}