{"id":"https://openalex.org/W2964355201","doi":"https://doi.org/10.1121/1.5118245","title":"Deep metric learning for bioacoustic classification: Overcoming training data scarcity using dynamic triplet loss","display_name":"Deep metric learning for bioacoustic classification: Overcoming training data scarcity using dynamic triplet loss","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2964355201","doi":"https://doi.org/10.1121/1.5118245","mag":"2964355201","pmid":"https://pubmed.ncbi.nlm.nih.gov/31370640"},"language":"en","primary_location":{"id":"doi:10.1121/1.5118245","doi":"https://doi.org/10.1121/1.5118245","is_oa":false,"landing_page_url":"https://doi.org/10.1121/1.5118245","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.10713","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Anshul Thakur","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Anshul Thakur","raw_affiliation_strings":["School of Computing and Electrical Engineering, IIT Mandi , Mandi, Himachal Pradesh-175005, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Electrical Engineering, IIT Mandi , Mandi, Himachal Pradesh-175005, India","institution_ids":["https://openalex.org/I9579091"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Daksh Thapar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Daksh Thapar","raw_affiliation_strings":["School of Computing and Electrical Engineering, IIT Mandi , Mandi, Himachal Pradesh-175005, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Electrical Engineering, IIT Mandi , Mandi, Himachal Pradesh-175005, India","institution_ids":["https://openalex.org/I9579091"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Padmanabhan Rajan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Padmanabhan Rajan","raw_affiliation_strings":["School of Computing and Electrical Engineering, IIT Mandi , Mandi, Himachal Pradesh-175005, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Electrical Engineering, IIT Mandi , Mandi, Himachal Pradesh-175005, India","institution_ids":["https://openalex.org/I9579091"]}]},{"author_position":"last","author":{"id":null,"display_name":"Aditya Nigam","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aditya Nigam","raw_affiliation_strings":["School of Computing and Electrical Engineering, IIT Mandi , Mandi, Himachal Pradesh-175005, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Electrical Engineering, IIT Mandi , Mandi, Himachal Pradesh-175005, India","institution_ids":["https://openalex.org/I9579091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9579091"],"apc_list":null,"apc_paid":null,"fwci":5.9092,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.96690203,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"146","issue":"1","first_page":"534","last_page":"547"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.0031999999191612005,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.002400000113993883,"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/bioacoustic-classification","display_name":"bioacoustic classification","score":0.9850000143051147},{"id":"https://openalex.org/keywords/deep-metric-learning","display_name":"deep metric learning","score":0.9919999837875366},{"id":"https://openalex.org/keywords/limited-training-data","display_name":"limited training data","score":0.7680000066757202},{"id":"https://openalex.org/keywords/multiscale-convolutional-neural-network","display_name":"multi-scale convolutional neural network","score":0.953000009059906},{"id":"https://openalex.org/keywords/open-set-recognition","display_name":"open-set recognition","score":0.8619999885559082},{"id":"https://openalex.org/keywords/animal-vocalizations","display_name":"animal vocalizations","score":0.42899999022483826}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.739300012588501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6341000199317932},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6105999946594238},{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.5688999891281128},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5443999767303467},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4830999970436096},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4778999984264374},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4666999876499176},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C187107819","wikidata":"https://www.wikidata.org/wiki/Q835696","display_name":"NASA Deep Space Network","level":3,"score":0.38830000162124634},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3068000078201294},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.28459998965263367},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2815000116825104},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.25999999046325684}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1121/1.5118245","doi":"https://doi.org/10.1121/1.5118245","is_oa":false,"landing_page_url":"https://doi.org/10.1121/1.5118245","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"},{"id":"pmid:31370640","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31370640","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"Journal Article"},{"id":"pmh:oai:arXiv.org:1903.10713","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.10713","pdf_url":"https://arxiv.org/pdf/1903.10713","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.1903.10713","doi":"https://doi.org/10.48550/arxiv.1903.10713","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.10713","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":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.10713","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.10713","pdf_url":"https://arxiv.org/pdf/1903.10713","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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W590468749","https://openalex.org/W1529830495","https://openalex.org/W2069943693","https://openalex.org/W2096733369","https://openalex.org/W2110090840","https://openalex.org/W2117863804","https://openalex.org/W2117965273","https://openalex.org/W2135442311","https://openalex.org/W2144005487","https://openalex.org/W2144513243","https://openalex.org/W2270409809","https://openalex.org/W2274287116","https://openalex.org/W2296751288","https://openalex.org/W2346062110","https://openalex.org/W2407513162","https://openalex.org/W2509065397","https://openalex.org/W2517817292","https://openalex.org/W2526050071","https://openalex.org/W2552032035","https://openalex.org/W2576474710","https://openalex.org/W2576656823","https://openalex.org/W2583643061","https://openalex.org/W2585877841","https://openalex.org/W2591013610","https://openalex.org/W2593610980","https://openalex.org/W2680737492","https://openalex.org/W2761083049","https://openalex.org/W2765532459","https://openalex.org/W2766759063","https://openalex.org/W2766893029","https://openalex.org/W2767010978","https://openalex.org/W2773441279","https://openalex.org/W2774918761","https://openalex.org/W2794193469","https://openalex.org/W2801347102","https://openalex.org/W2883595988","https://openalex.org/W2889095810","https://openalex.org/W2889307828","https://openalex.org/W2889994223","https://openalex.org/W2890012819","https://openalex.org/W2891247746","https://openalex.org/W2963723765","https://openalex.org/W2964355201"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W3196596949","https://openalex.org/W4226304637","https://openalex.org/W2966207284","https://openalex.org/W3099765033","https://openalex.org/W4223631995","https://openalex.org/W2763440672","https://openalex.org/W1534179852","https://openalex.org/W3170449064","https://openalex.org/W2024941537"],"abstract_inverted_index":{"Bioacoustic":[0],"classification":[1,159,181],"often":[2],"suffers":[3],"from":[4],"the":[5,12,26,60,65,127,136,151,165,183],"lack":[6],"of":[7,15,44,64,90,121,167],"labeled":[8],"data.":[9],"This":[10],"hinders":[11],"effective":[13,36],"utilization":[14],"state-of-the-art":[16],"deep":[17,30,97,116],"learning":[18,91],"models":[19],"in":[20,139,174],"bioacoustics.":[21],"To":[22],"overcome":[23],"this":[24,92],"problem,":[25],"authors":[27],"propose":[28],"a":[29,41,54,70,84,109,112],"metric":[31,98,117],"learning-based":[32],"framework":[33,52,153,185],"that":[34,150],"provides":[35],"classification,":[37],"even":[38],"when":[39],"only":[40],"small":[42],"number":[43,120],"per-class":[45],"training":[46],"examples":[47,105],"are":[48],"available.":[49],"The":[50,88,100,119],"proposed":[51,61,152,184],"utilizes":[53],"multiscale":[55],"convolutional":[56],"neural":[57],"network":[58],"and":[59,78],"dynamic":[62,168],"variant":[63],"triplet":[66,101,131,169],"loss":[67,102,132,138,170,173],"to":[68,107,114,189],"learn":[69],"transformation":[71,93],"space":[72],"where":[73],"intra-class":[74],"separation":[75,80],"is":[76,81,94],"minimized":[77],"inter-class":[79],"maximized":[82],"by":[83],"dynamically":[85],"increasing":[86],"margin.":[87],"process":[89],"known":[95],"as":[96,108],"learning.":[99,118],"analyzes":[103],"three":[104,144],"(referred":[106],"triplet)":[110],"at":[111],"time":[113],"perform":[115],"possible":[122],"triplets":[123],"increases":[124],"cubically":[125],"with":[126],"dataset":[128],"size,":[129],"making":[130],"more":[133],"suitable":[134],"than":[135,156],"cross-entropy":[137,172],"data-scarce":[140,175],"conditions.":[141,176],"Experiments":[142],"on":[143],"different":[145],"publicly":[146],"available":[147],"datasets":[148],"show":[149],"performs":[154],"better":[155],"existing":[157,179],"bioacoustic":[158,180],"methods.":[160],"Experimental":[161],"results":[162],"also":[163],"demonstrate":[164],"superiority":[166],"over":[171],"Furthermore,":[177],"unlike":[178],"methods,":[182],"has":[186],"been":[187],"extended":[188],"provide":[190],"open-set":[191],"classification.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2019-08-13T00:00:00"}