{"id":"https://openalex.org/W7143498775","doi":"https://doi.org/10.48550/arxiv.2603.26389","title":"Maintaining Difficulty: A Margin Scheduler for Triplet Loss in Siamese Networks Training","display_name":"Maintaining Difficulty: A Margin Scheduler for Triplet Loss in Siamese Networks Training","publication_year":2026,"publication_date":"2026-03-27","ids":{"openalex":"https://openalex.org/W7143498775","doi":"https://doi.org/10.48550/arxiv.2603.26389"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.26389","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26389","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,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.26389","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117711556","display_name":"Roberto Sprengel Minozzo Tomchak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomchak, Roberto Sprengel Minozzo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130991491","display_name":"Oge Marques","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marques, Oge","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060672104","display_name":"Lucas Garcia Pedroso","orcid":"https://orcid.org/0009-0003-1516-119X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pedroso, Lucas Garcia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130941261","display_name":"Luiz Eduardo Oliveira","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oliveira, Luiz Eduardo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5107662769","display_name":"Paulo Lisboa de Almeida","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"de Almeida, Paulo Lisboa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"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":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.1436000019311905,"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":0.1436000019311905,"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":0.11569999903440475,"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/T12676","display_name":"Machine Learning and ELM","score":0.09929999709129333,"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/margin","display_name":"Margin (machine learning)","score":0.9316999912261963},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5812000036239624},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.5220999717712402},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5056999921798706},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.47519999742507935},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.45989999175071716},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.45910000801086426}],"concepts":[{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.9316999912261963},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5812000036239624},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5099999904632568},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5056999921798706},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.47519999742507935},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.45910000801086426},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4560000002384186},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.4180000126361847},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3646000027656555},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3231000006198883},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28760001063346863},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2694000005722046},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C39891107","wikidata":"https://www.wikidata.org/wiki/Q5767098","display_name":"Hinge loss","level":3,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.26389","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26389","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,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.26389","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26389","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,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"Triplet":[1],"Margin":[2],"Ranking":[3],"Loss":[4],"is":[5,78],"one":[6],"of":[7,58,66,73,107,113,123],"the":[8,35,55,63,85,91,105,111,121,132],"most":[9],"widely":[10],"used":[11],"loss":[12,25],"functions":[13],"in":[14,161],"Siamese":[15],"Networks":[16],"for":[17],"solving":[18],"Distance":[19],"Metric":[20],"Learning":[21],"(DML)":[22],"problems.":[23],"This":[24,80],"function":[26],"depends":[27],"on":[28,95,154],"a":[29,70,100,143,147],"margin":[30,57,77,86,101,145,150],"parameter":[31],"\u03bc,":[32,67],"which":[33],"defines":[34],"minimum":[36],"distance":[37],"that":[38,69,83,103,131],"should":[39],"separate":[40],"positive":[41],"and":[42,146],"negative":[43],"pairs":[44],"during":[45,53],"training.":[46],"In":[47],"this":[48,76,96],"work,":[49],"we":[50,98],"show":[51,130,158],"that,":[52],"training,":[54],"effective":[56],"many":[59],"triplets":[60,74,115],"often":[61],"exceeds":[62],"predefined":[64],"value":[65,106],"provided":[68],"sufficient":[71],"number":[72],"violating":[75],"observed.":[79],"behavior":[81],"indicates":[82],"fixing":[84],"throughout":[87],"training":[88,125],"may":[89],"limit":[90],"learning":[92],"process.":[93],"Based":[94],"observation,":[97],"propose":[99],"scheduler":[102],"adjusts":[104],"\u03bc":[108],"according":[109],"to":[110,136,141],"proportion":[112],"easy":[114],"observed":[116],"at":[117],"each":[118],"epoch,":[119],"with":[120],"goal":[122],"maintaining":[124],"difficulty":[126],"over":[127],"time.":[128],"We":[129],"proposed":[133],"strategy":[134],"leads":[135],"improved":[137],"performance":[138],"when":[139],"compared":[140],"both":[142],"constant":[144],"monotonically":[148],"increasing":[149],"scheme.":[151],"Experimental":[152],"results":[153],"four":[155],"different":[156],"datasets":[157],"consistent":[159],"gains":[160],"verification":[162],"performance.":[163]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-31T00:00:00"}