{"id":"https://openalex.org/W3193282739","doi":"https://doi.org/10.1109/icip42928.2021.9506428","title":"Margin Loss Based On Adaptive Metric For Image Recognition","display_name":"Margin Loss Based On Adaptive Metric For Image Recognition","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3193282739","doi":"https://doi.org/10.1109/icip42928.2021.9506428","mag":"3193282739"},"language":"en","primary_location":{"id":"doi:10.1109/icip42928.2021.9506428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100394554","display_name":"Zhihong Liu","orcid":"https://orcid.org/0000-0001-6093-0726"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhihong Liu","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School"],"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School","institution_ids":["https://openalex.org/I4210114105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027971286","display_name":"Lei Song","orcid":"https://orcid.org/0000-0001-7108-2232"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Song","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School"],"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School","institution_ids":["https://openalex.org/I4210114105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059112338","display_name":"Xiaowan Hu","orcid":"https://orcid.org/0000-0001-7364-4489"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowan Hu","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School"],"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School","institution_ids":["https://openalex.org/I4210114105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028229824","display_name":"Haoqian Wang","orcid":"https://orcid.org/0000-0003-2792-8469"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoqian Wang","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School"],"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School","institution_ids":["https://openalex.org/I4210114105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100394554"],"corresponding_institution_ids":["https://openalex.org/I4210114105"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09580065,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":null,"first_page":"2878","last_page":"2882"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9994999766349792,"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/discriminative-model","display_name":"Discriminative model","score":0.8834609985351562},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.8609672784805298},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.7124664783477783},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6977866888046265},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.682828426361084},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6811972260475159},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6266379356384277},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.6228584051132202},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.606803834438324},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.49368008971214294},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.45615899562835693},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42729029059410095},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.396171510219574},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20263126492500305},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.1644200086593628},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10702809691429138}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8834609985351562},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8609672784805298},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7124664783477783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6977866888046265},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.682828426361084},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6811972260475159},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6266379356384277},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.6228584051132202},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.606803834438324},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.49368008971214294},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.45615899562835693},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42729029059410095},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.396171510219574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20263126492500305},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.1644200086593628},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10702809691429138},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip42928.2021.9506428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2096733369","https://openalex.org/W2106053110","https://openalex.org/W2144172034","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2520774990","https://openalex.org/W2609575245","https://openalex.org/W2922509574","https://openalex.org/W2949007385","https://openalex.org/W2962898354","https://openalex.org/W2963224870","https://openalex.org/W2963420686","https://openalex.org/W2963466847","https://openalex.org/W2963656735","https://openalex.org/W2963814162","https://openalex.org/W2969985801","https://openalex.org/W3101227480","https://openalex.org/W3118608800","https://openalex.org/W6675751002","https://openalex.org/W6681239517","https://openalex.org/W6684191040","https://openalex.org/W6726946684","https://openalex.org/W6735013348","https://openalex.org/W6736780073","https://openalex.org/W6743731764","https://openalex.org/W6748257384","https://openalex.org/W6751593755"],"related_works":["https://openalex.org/W4283819496","https://openalex.org/W3095152779","https://openalex.org/W3119773509","https://openalex.org/W3128220219","https://openalex.org/W4367154275","https://openalex.org/W2913125146","https://openalex.org/W2911303748","https://openalex.org/W4367361129","https://openalex.org/W2761785940","https://openalex.org/W4391307109"],"abstract_inverted_index":{"Cross-entropy":[0],"(CE)":[1],"loss":[2,20,33],"is":[3,136],"one":[4],"of":[5,53,73,108,128],"the":[6,15,30,71,87,106,125,133],"most":[7],"commonly":[8],"used":[9],"supervision":[10],"in":[11,75],"image":[12,140],"recognition.":[13,141],"However,":[14],"features":[16,74,129],"trained":[17],"by":[18],"CE":[19,32],"are":[21,26,58],"not":[22],"discriminative":[23,37,126],"enough.":[24],"There":[25],"many":[27],"methods":[28,41],"using":[29],"angular-softmax":[31],"to":[34,69,85],"learn":[35],"angularly":[36],"features.":[38,90],"But":[39],"these":[40],"still":[42],"use":[43],"manually":[44],"designed":[45],"metric,":[46],"which":[47,95],"cannot":[48],"deal":[49],"with":[50],"complicated":[51],"distribution":[52,72,127],"high-dimensional":[54],"features,":[55],"and":[56,81,100,112,115],"there":[57],"no":[59],"appropriate":[60],"inter-class":[61,98],"restraint.":[62],"Therefore,":[63],"we":[64,92],"propose":[65],"a":[66],"novel":[67],"method":[68,117,135],"restrain":[70],"high-dimensional.":[76],"We":[77,104,122],"construct":[78],"trainable":[79],"centers,":[80],"design":[82,93],"adaptive":[83],"metric":[84],"express":[86],"distance":[88,99,102],"between":[89],"Specifically,":[91],"AdaMetricLoss":[94,109],"can":[96],"manipulate":[97],"intra-class":[101],"simultaneously.":[103],"evaluate":[105],"effectiveness":[107],"on":[110,130],"Cifar10":[111],"Cifar100":[113],"datasets,":[114],"our":[116],"shows":[118],"preferable":[119],"classification":[120],"performance.":[121],"also":[123],"visualize":[124],"MNIST,":[131],"proves":[132],"proposed":[134],"more":[137],"suitable":[138],"for":[139]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}