{"id":"https://openalex.org/W3080164465","doi":"https://doi.org/10.1109/tai.2020.3026982","title":"Unsupervised Deep Metric Learning via Orthogonality Based Probabilistic Loss","display_name":"Unsupervised Deep Metric Learning via Orthogonality Based Probabilistic Loss","alternate_titles":[],"publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3080164465","doi":"https://doi.org/10.1109/tai.2020.3026982","mag":"3080164465"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2020.3026982","doi":"https://doi.org/10.1109/tai.2020.3026982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2020.3026982","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1","poland-20"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"},"parent_works":[],"lineage":["https://openalex.org/W3080164465"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.09880","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038904282","display_name":"Ujjal Kr Dutta","orcid":"https://orcid.org/0000-0002-0470-5521","observed_orcids":["https://orcid.org/0000-0002-0470-5521"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ujjal Kr Dutta","raw_affiliation_strings":["Myntra Designs, Bangalore, India"],"raw_orcid":"https://orcid.org/0000-0002-0470-5521","affiliations":[{"raw_affiliation_string":"Myntra Designs, Bangalore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021790939","display_name":"Mehrtash Tafazzoli Harandi","orcid":"https://orcid.org/0000-0002-6937-6300","observed_orcids":["https://orcid.org/0000-0002-6937-6300"]},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mehrtash Harandi","raw_affiliation_strings":["Monash University, Melbourne, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6937-6300","affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chellu Chandra Sekhar","orcid":"https://orcid.org/0000-0001-9049-1912","observed_orcids":["https://orcid.org/0000-0001-9049-1912"]},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chellu Chandra Sekhar","raw_affiliation_strings":["Indian Institute of Technology Madras, Chennai, India"],"raw_orcid":"https://orcid.org/0000-0001-9049-1912","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":1.3275,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.80136891,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"1","issue":"1","first_page":"74","last_page":"84"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.396699994802475,"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/T10057","display_name":"Face and Expression Recognition","score":0.396699994802475,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1770000010728836,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0851999968290329,"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/deep-metric-learning","display_name":"deep metric learning","score":0.8289999961853027},{"id":"https://openalex.org/keywords/orthogonality-constraints","display_name":"orthogonality constraints","score":0.9129999876022339},{"id":"https://openalex.org/keywords/pseudo-labeling","display_name":"pseudo-labeling","score":0.781000018119812},{"id":"https://openalex.org/keywords/graph-clustering","display_name":"graph clustering","score":0.984000027179718},{"id":"https://openalex.org/keywords/triplet-loss","display_name":"triplet loss","score":0.8330000042915344},{"id":"https://openalex.org/keywords/angular-constraints","display_name":"angular constraints","score":0.7870000004768372},{"id":"https://openalex.org/keywords/model-collapse","display_name":"model collapse","score":0.7210000157356262},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"stochastic optimization","score":0.6140000224113464},{"id":"https://openalex.org/keywords/large-scale-datasets","display_name":"large-scale datasets","score":0.8410000205039978}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7699000239372253},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.7494000196456909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.632099986076355},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6037999987602234},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6018000245094299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5843999981880188},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5595999956130981},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5328999757766724},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5026999711990356},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4781999886035919},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4702000021934509},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33379998803138733},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3000999987125397},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.2759000062942505},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2572999894618988}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tai.2020.3026982","doi":"https://doi.org/10.1109/tai.2020.3026982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2020.3026982","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1","poland-20"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2008.09880","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.09880","pdf_url":"https://arxiv.org/pdf/2008.09880","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2008.09880","doi":"https://doi.org/10.48550/arxiv.2008.09880","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.09880","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.09880","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.09880","pdf_url":"https://arxiv.org/pdf/2008.09880","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3080164465.pdf","grobid_xml":"https://content.openalex.org/works/W3080164465.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W1804110266","https://openalex.org/W1875842236","https://openalex.org/W1963882359","https://openalex.org/W2034014085","https://openalex.org/W2096733369","https://openalex.org/W2097117768","https://openalex.org/W2103250033","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2126579184","https://openalex.org/W2133126147","https://openalex.org/W2137145201","https://openalex.org/W2138011018","https://openalex.org/W2138674039","https://openalex.org/W2142992480","https://openalex.org/W2144796873","https://openalex.org/W2154872931","https://openalex.org/W2157364932","https://openalex.org/W2167623372","https://openalex.org/W2174726731","https://openalex.org/W2176040302","https://openalex.org/W2518754566","https://openalex.org/W2549348365","https://openalex.org/W2555897561","https://openalex.org/W2559091987","https://openalex.org/W2615981376","https://openalex.org/W2652783164","https://openalex.org/W2750384547","https://openalex.org/W2783165089","https://openalex.org/W2788015283","https://openalex.org/W2794764818","https://openalex.org/W2795246076","https://openalex.org/W2798738034","https://openalex.org/W2798991696","https://openalex.org/W2807757380","https://openalex.org/W2883725317","https://openalex.org/W2892246301","https://openalex.org/W2901038558","https://openalex.org/W2928151272","https://openalex.org/W2945070549","https://openalex.org/W2950180292","https://openalex.org/W2953066166","https://openalex.org/W2962837320","https://openalex.org/W2963271919","https://openalex.org/W2963499153","https://openalex.org/W2963891777","https://openalex.org/W2963988212","https://openalex.org/W2964172727","https://openalex.org/W2964271799","https://openalex.org/W2965318645","https://openalex.org/W2979579363","https://openalex.org/W2997944991","https://openalex.org/W3035014997","https://openalex.org/W4237044863","https://openalex.org/W4285719527","https://openalex.org/W6600609147","https://openalex.org/W7064683377"],"related_works":["https://openalex.org/W4409263366","https://openalex.org/W7095721347","https://openalex.org/W3161534537","https://openalex.org/W2984693480","https://openalex.org/W2997290266","https://openalex.org/W3163470720","https://openalex.org/W3118603955","https://openalex.org/W2809627483","https://openalex.org/W3015569265","https://openalex.org/W4312683787"],"abstract_inverted_index":{"Metric":[0],"learning":[1,19,46,88],"is":[2,30,63],"an":[3,44,104,111],"important":[4],"problem":[5],"in":[6,114],"machine":[7],"learning.":[8],"It":[9],"aims":[10],"to":[11,24,35,79,134,137],"group":[12],"similar":[13],"observations":[14],"together.":[15],"Existing":[16],"state-of-the-art":[17,149],"metric":[18,51,87],"approaches":[20],"require":[21],"class":[22,56,61],"labels":[23,62],"induce":[25],"a":[26,50,71,92,122,128],"metric.":[27],"Sometimes":[28],"it":[29],"expensive":[31],"or":[32],"not":[33],"possible":[34],"collect":[36],"these":[37],"labels.":[38,57],"In":[39],"this":[40],"paper,":[41],"we":[42],"propose":[43,91],"unsupervised":[45],"approach":[47,147],"that":[48,96],"learns":[49],"without":[52],"making":[53],"use":[54],"of":[55,60,68,82,100,131,145],"The":[58,75],"lack":[59],"compensated":[64],"by":[65],"obtaining":[66],"pseudo-labels":[67,76],"data":[69],"using":[70],"graph-based":[72],"clustering":[73],"approach.":[74],"are":[77],"used":[78],"form":[80],"triplets":[81],"examples,":[83],"which":[84],"guide":[85],"the":[86,98,115,143],"process.":[89],"We":[90,125],"probabilistic":[93],"loss":[94],"function":[95,109],"minimizes":[97],"chances":[99],"each":[101],"triplet":[102],"violating":[103],"angular":[105],"constraint.":[106],"A":[107],"weight":[108],"and":[110,120],"orthogonality":[112],"constraint":[113],"objective":[116],"speed":[117],"up":[118,136],"convergence":[119],"avoid":[121],"model":[123],"collapse.":[124],"also":[126],"provide":[127],"stochastic":[129],"formulation":[130],"our":[132,146],"method":[133],"scale":[135],"large-scale":[138],"datasets.":[139],"Our":[140],"studies":[141],"demonstrate":[142],"competitiveness":[144],"against":[148],"methods.":[150]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3080164465","counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2020-09-01T00:00:00"}
