{"id":"https://openalex.org/W4416953834","doi":"https://doi.org/10.3390/info16121068","title":"LossTransform: Reformulating the Loss Function for Contrastive Learning","display_name":"LossTransform: Reformulating the Loss Function for Contrastive Learning","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4416953834","doi":"https://doi.org/10.3390/info16121068"},"language":"en","primary_location":{"id":"doi:10.3390/info16121068","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16121068","pdf_url":"https://www.mdpi.com/2078-2489/16/12/1068/pdf?version=1764771939","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/16/12/1068/pdf?version=1764771939","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073088550","display_name":"Zheng Li","orcid":"https://orcid.org/0009-0004-2111-4047"},"institutions":[{"id":"https://openalex.org/I4210104314","display_name":"New York Institute of Technology","ror":"https://ror.org/01bghzb51","country_code":"US","type":"education","lineage":["https://openalex.org/I4210104314"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng Li","raw_affiliation_strings":["Department of Computer Science, New York Institute of Technology, New York, NY 10023, USA"],"raw_orcid":"https://orcid.org/0009-0004-2111-4047","affiliations":[{"raw_affiliation_string":"Department of Computer Science, New York Institute of Technology, New York, NY 10023, USA","institution_ids":["https://openalex.org/I4210104314"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085616097","display_name":"Jerry Cheng","orcid":"https://orcid.org/0000-0002-3968-9699"},"institutions":[{"id":"https://openalex.org/I4210104314","display_name":"New York Institute of Technology","ror":"https://ror.org/01bghzb51","country_code":"US","type":"education","lineage":["https://openalex.org/I4210104314"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jerry Cheng","raw_affiliation_strings":["Department of Computer Science, New York Institute of Technology, New York, NY 10023, USA"],"raw_orcid":"https://orcid.org/0000-0002-3968-9699","affiliations":[{"raw_affiliation_string":"Department of Computer Science, New York Institute of Technology, New York, NY 10023, USA","institution_ids":["https://openalex.org/I4210104314"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105836405","display_name":"Huanying Gu","orcid":"https://orcid.org/0009-0005-9510-6696"},"institutions":[{"id":"https://openalex.org/I4210104314","display_name":"New York Institute of Technology","ror":"https://ror.org/01bghzb51","country_code":"US","type":"education","lineage":["https://openalex.org/I4210104314"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Huanying Helen Gu","raw_affiliation_strings":["Department of Computer Science, New York Institute of Technology, New York, NY 10023, USA"],"raw_orcid":"https://orcid.org/0009-0005-9510-6696","affiliations":[{"raw_affiliation_string":"Department of Computer Science, New York Institute of Technology, New York, NY 10023, USA","institution_ids":["https://openalex.org/I4210104314"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5105836405"],"corresponding_institution_ids":["https://openalex.org/I4210104314"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36393113,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"12","first_page":"1068","last_page":"1068"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5652999877929688,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.5652999877929688,"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":0.3068000078201294,"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/T11448","display_name":"Face recognition and analysis","score":0.030400000512599945,"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/sample","display_name":"Sample (material)","score":0.6238999962806702},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5329999923706055},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5286999940872192},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.41620001196861267},{"id":"https://openalex.org/keywords/contrastive-analysis","display_name":"Contrastive analysis","score":0.4002000093460083},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3352999985218048}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6654999852180481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6381000280380249},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6238999962806702},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5329999923706055},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5286999940872192},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47940000891685486},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.41620001196861267},{"id":"https://openalex.org/C2777629044","wikidata":"https://www.wikidata.org/wiki/Q614959","display_name":"Contrastive analysis","level":2,"score":0.4002000093460083},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30320000648498535},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2980000078678131},{"id":"https://openalex.org/C3020318244","wikidata":"https://www.wikidata.org/wiki/Q4812187","display_name":"Large sample","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.28040000796318054},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2685000002384186}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/info16121068","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16121068","pdf_url":"https://www.mdpi.com/2078-2489/16/12/1068/pdf?version=1764771939","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:265554492d8641d5bdd3c6a0fe5d0529","is_oa":true,"landing_page_url":"https://doaj.org/article/265554492d8641d5bdd3c6a0fe5d0529","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 16, Iss 12, p 1068 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/info16121068","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16121068","pdf_url":"https://www.mdpi.com/2078-2489/16/12/1068/pdf?version=1764771939","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416953834.pdf","grobid_xml":"https://content.openalex.org/works/W4416953834.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1934992405","https://openalex.org/W2031489346","https://openalex.org/W2047839530","https://openalex.org/W2097117768","https://openalex.org/W2117539524","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2963125010","https://openalex.org/W2963150697","https://openalex.org/W2963446712","https://openalex.org/W2963918968","https://openalex.org/W2964081807","https://openalex.org/W2964137095","https://openalex.org/W2970602317","https://openalex.org/W3034368386","https://openalex.org/W3035682985","https://openalex.org/W3128661784","https://openalex.org/W3145450063","https://openalex.org/W4214592090","https://openalex.org/W4292787282","https://openalex.org/W4307823382","https://openalex.org/W4312443924"],"related_works":[],"abstract_inverted_index":{"Contrastive":[0],"learning":[1,71],"improves":[2,94],"model":[3,138],"performance":[4,130,139],"by":[5,96],"differentiating":[6],"between":[7],"positive":[8,58],"and":[9,32,43,61,87,103,127,133,140,150],"negative":[10],"sample":[11,59,80],"pairs.":[12],"However,":[13],"its":[14,36],"application":[15],"is":[16,121],"primarily":[17],"confined":[18],"to":[19,35,39,72,105],"classification":[20],"tasks,":[21,112],"facing":[22],"challenges":[23],"with":[24,123],"complex":[25,134],"recognition":[26],"tasks":[27],"such":[28],"as":[29],"object":[30,88],"detection":[31,89,111],"segmentation":[33],"due":[34],"limited":[37],"capacity":[38],"capture":[40],"spatial":[41],"relationships":[42],"fine-grained":[44],"features.":[45],"To":[46],"address":[47],"this":[48,145],"limitation,":[49],"we":[50],"propose":[51],"LossTransform,":[52],"a":[53,63],"novel":[54,64],"approach":[55],"that":[56,92,119],"redefines":[57],"pairs":[60],"establishes":[62],"contrastive":[65,70],"loss":[66],"paradigm.":[67],"LossTransform":[68,93,120],"advances":[69],"the":[73,78],"instance":[74],"level,":[75],"departing":[76],"from":[77],"traditional":[79],"level.":[81],"Empirical":[82],"evaluations":[83],"on":[84,98,101,110],"ImageNet,":[85,102],"CIFAR,":[86,99],"benchmarks":[90],"indicate":[91],"accuracy":[95],"+2.73%":[97],"+2.52%":[100],"up":[104],"+5.2%":[106],"in":[107],"average":[108],"precision":[109],"while":[113],"maintaining":[114],"efficiency.":[115],"These":[116],"results":[117],"illustrate":[118],"compatible":[122],"large-scale":[124],"training":[125,143],"pipelines":[126],"exhibits":[128],"robust":[129],"across":[131],"diverse":[132],"datasets.":[135],"By":[136],"optimizing":[137],"significantly":[141],"reducing":[142],"time,":[144],"research":[146],"enables":[147],"more":[148],"efficient":[149],"accessible":[151],"solutions":[152],"for":[153],"societal":[154],"applications.":[155]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-12-03T00:00:00"}