{"id":"https://openalex.org/W7164345568","doi":"https://doi.org/10.48550/arxiv.2606.11233","title":"OSCS-SupCon: Orthogonal Sigmoid-based Common and Style Supervised Contrastive Learning for Robust Feature Disentanglement","display_name":"OSCS-SupCon: Orthogonal Sigmoid-based Common and Style Supervised Contrastive Learning for Robust Feature Disentanglement","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7164345568","doi":"https://doi.org/10.48550/arxiv.2606.11233"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.11233","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11233","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"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.2606.11233","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138395040","display_name":"Bin Wang (30851)","orcid":"https://orcid.org/0009-0005-0589-3551"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Bin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138423641","display_name":"Fadi Dornaika","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dornaika, Fadi","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":0.6036999821662903,"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":0.6036999821662903,"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":0.1096000000834465,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0658000037074089,"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/orthogonality","display_name":"Orthogonality","score":0.7623999714851379},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.7454000115394592},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6186000108718872},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5669999718666077},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5557000041007996},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5080000162124634},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.39570000767707825},{"id":"https://openalex.org/keywords/linear-subspace","display_name":"Linear subspace","score":0.38420000672340393}],"concepts":[{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.7623999714851379},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7454000115394592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6927000284194946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6384000182151794},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6186000108718872},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5669999718666077},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5557000041007996},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5080000162124634},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.38029998540878296},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36880001425743103},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.3418999910354614},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2689000070095062},{"id":"https://openalex.org/C153874254","wikidata":"https://www.wikidata.org/wiki/Q115542","display_name":"Canonical correlation","level":2,"score":0.26159998774528503}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.11233","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11233","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.11233","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11233","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.7254572510719299,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Supervised":[0,69],"Contrastive":[1,70],"Learning":[2],"(SupCon)":[3],"has":[4],"achieved":[5],"strong":[6],"performance":[7],"by":[8,27,36],"explicitly":[9],"modeling":[10],"pairwise":[11,79,103],"relationships":[12],"among":[13],"samples.":[14],"However,":[15],"existing":[16],"SupCon-based":[17],"methods":[18,152],"suffer":[19],"from":[20],"two":[21,94],"key":[22],"limitations:":[23],"negative-sample":[24,108],"dilution":[25],"induced":[26],"the":[28,37,160,168,190],"standard":[29],"InfoNCE":[30],"loss,":[31],"and":[32,45,54,67,98,106,116,131,183],"feature-space":[33],"entanglement":[34],"caused":[35],"lack":[38],"of":[39,134,192],"explicit":[40,83],"constraints":[41],"separating":[42],"category-relevant":[43],"(common)":[44],"category-irrelevant":[46],"(style)":[47],"features.":[48],"These":[49],"limitations":[50],"reduce":[51],"feature":[52,118,129],"discriminability":[53],"generalization":[55,184],"ability.":[56],"To":[57],"address":[58],"these":[59],"issues,":[60],"we":[61,87,111],"propose":[62],"OSCS-SupCon":[63,145],"(Orthogonal":[64],"Sigmoid-based":[65],"Common":[66],"Style":[68],"Learning),":[71],"a":[72,77,89,121,165,172],"unified":[73],"framework":[74],"that":[75,144],"combines":[76],"sigmoid-based":[78,90],"contrastive":[80,91,150],"objective":[81],"with":[82,93,124,164],"orthogonality":[84,113],"constraints.":[85],"Specifically,":[86],"introduce":[88],"loss":[92],"learnable":[95],"parameters,":[96],"temperature":[97],"bias,":[99],"which":[100],"adaptively":[101],"modulate":[102],"decision":[104],"boundaries":[105],"alleviate":[107],"dilution.":[109],"Furthermore,":[110],"enforce":[112],"between":[114],"common":[115],"style":[117],"subspaces":[119],"via":[120],"linear":[122],"projection":[123],"ReLU":[125],"nonlinearity,":[126],"thereby":[127],"reducing":[128],"overlap":[130],"improving":[132],"disentanglement":[133],"style-irrelevant":[135],"representations.":[136],"Extensive":[137],"experiments":[138],"on":[139,159],"six":[140],"benchmark":[141],"datasets":[142],"demonstrate":[143],"consistently":[146],"outperforms":[147],"state-of-the-art":[148],"supervised":[149],"learning":[151],"across":[153],"multiple":[154],"backbone":[155],"architectures.":[156],"In":[157],"particular,":[158],"fine-grained":[161],"CUB200-2011":[162],"dataset":[163],"ResNet-18":[166],"backbone,":[167],"proposed":[169],"method":[170],"achieves":[171],"3.4%":[173],"improvement":[174],"in":[175],"classification":[176],"accuracy":[177],"over":[178],"CS-SupCon,":[179],"highlighting":[180],"its":[181],"robustness":[182],"capability.":[185],"Ablation":[186],"studies":[187],"further":[188],"confirm":[189],"effectiveness":[191],"each":[193],"component.":[194]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-12T00:00:00"}