{"id":"https://openalex.org/W3090557174","doi":"https://doi.org/10.1109/icip40778.2020.9191197","title":"Deep Subclass Linear Discriminant Analysis For Multimodal Feature Space Learning","display_name":"Deep Subclass Linear Discriminant Analysis For Multimodal Feature Space Learning","publication_year":2020,"publication_date":"2020-09-30","ids":{"openalex":"https://openalex.org/W3090557174","doi":"https://doi.org/10.1109/icip40778.2020.9191197","mag":"3090557174"},"language":"en","primary_location":{"id":"doi:10.1109/icip40778.2020.9191197","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9191197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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/A5045397738","display_name":"Abin Jose","orcid":"https://orcid.org/0000-0002-3974-3552"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Abin Jose","raw_affiliation_strings":["Institut fur Nachrichtentechnik, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Institut fur Nachrichtentechnik, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013074509","display_name":"Yan Shen","orcid":"https://orcid.org/0009-0000-1536-979X"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shen Yan","raw_affiliation_strings":["Michigan State University, East Lansing, USA"],"affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675021","display_name":"Mi Zhang","orcid":"https://orcid.org/0000-0003-1584-2799"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mi Zhang","raw_affiliation_strings":["Michigan State University, East Lansing, USA"],"affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105716901","display_name":"Jens-Rainer Ohm","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jens-Rainer Ohm","raw_affiliation_strings":["Institut fur Nachrichtentechnik, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Institut fur Nachrichtentechnik, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045397738"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10610338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs 1511 4707","issue":null,"first_page":"1701","last_page":"1705"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","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"}},"topics":[{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994000196456909,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9976000189781189,"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/discriminative-model","display_name":"Discriminative model","score":0.7763655781745911},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.742332935333252},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7301856279373169},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.7102115750312805},{"id":"https://openalex.org/keywords/subclass","display_name":"Subclass","score":0.6510528922080994},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5645549893379211},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5580141544342041},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.52684485912323},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.4818614423274994},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48154503107070923},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4549734592437744},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4498717188835144},{"id":"https://openalex.org/keywords/scatter-matrix","display_name":"Scatter matrix","score":0.4446905255317688},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4415399134159088},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4408404231071472},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.4324554204940796},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.43125927448272705},{"id":"https://openalex.org/keywords/discriminant","display_name":"Discriminant","score":0.4306832253932953},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41283735632896423},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.388708233833313}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7763655781745911},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.742332935333252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7301856279373169},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.7102115750312805},{"id":"https://openalex.org/C2776194381","wikidata":"https://www.wikidata.org/wiki/Q3965271","display_name":"Subclass","level":3,"score":0.6510528922080994},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5645549893379211},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5580141544342041},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.52684485912323},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.4818614423274994},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48154503107070923},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4549734592437744},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4498717188835144},{"id":"https://openalex.org/C176917957","wikidata":"https://www.wikidata.org/wiki/Q7430596","display_name":"Scatter matrix","level":4,"score":0.4446905255317688},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4415399134159088},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4408404231071472},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.4324554204940796},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.43125927448272705},{"id":"https://openalex.org/C78397625","wikidata":"https://www.wikidata.org/wiki/Q192487","display_name":"Discriminant","level":2,"score":0.4306832253932953},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41283735632896423},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.388708233833313},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.0},{"id":"https://openalex.org/C159654299","wikidata":"https://www.wikidata.org/wiki/Q79460","display_name":"Antibody","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C177384507","wikidata":"https://www.wikidata.org/wiki/Q1149000","display_name":"Multivariate normal distribution","level":3,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C203014093","wikidata":"https://www.wikidata.org/wiki/Q101929","display_name":"Immunology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip40778.2020.9191197","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9191197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W101693742","https://openalex.org/W1979902991","https://openalex.org/W2001619934","https://openalex.org/W2034230010","https://openalex.org/W2064031858","https://openalex.org/W2096733369","https://openalex.org/W2108598243","https://openalex.org/W2116423617","https://openalex.org/W2121647436","https://openalex.org/W2135346934","https://openalex.org/W2144935315","https://openalex.org/W2145901830","https://openalex.org/W2151543530","https://openalex.org/W2164552042","https://openalex.org/W2177287823","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2589177632","https://openalex.org/W2808388233","https://openalex.org/W2962837320","https://openalex.org/W2962887033","https://openalex.org/W2963892472","https://openalex.org/W3099206234","https://openalex.org/W4293380554","https://openalex.org/W4298379700","https://openalex.org/W6604126237","https://openalex.org/W6676297131","https://openalex.org/W6678140244","https://openalex.org/W6680962578","https://openalex.org/W6692658850","https://openalex.org/W6693735323"],"related_works":["https://openalex.org/W2383679030","https://openalex.org/W2152736741","https://openalex.org/W2104382484","https://openalex.org/W2391958148","https://openalex.org/W2364059254","https://openalex.org/W1862960822","https://openalex.org/W2168411768","https://openalex.org/W2390831622","https://openalex.org/W2115521736","https://openalex.org/W3140864443"],"abstract_inverted_index":{"In":[0],"this":[1,25],"work,":[2],"we":[3,18,27],"target":[4],"a":[5],"known":[6],"problem":[7],"in":[8,89],"representation":[9,81],"learning":[10,109],"that":[11,97],"is:":[12],"beyond":[13],"coarse":[14],"classification,":[15],"how":[16],"can":[17],"better":[19],"model":[20],"fine-grained":[21,105],"categorization?":[22],"To":[23],"address":[24],"problem,":[26],"introduce":[28],"Deep":[29],"Subclass":[30],"Linear":[31],"Discriminant":[32],"Analysis":[33],"(DeepSDA),":[34],"which":[35],"utilizes":[36],"intra-class":[37],"variation":[38],"and":[39,57,83,107],"inter-class":[40],"similarity":[41],"during":[42],"training.":[43],"We":[44,61,95],"could":[45],"achieve":[46],"multimodal":[47],"classification":[48],"by":[49],"maximizing":[50],"the":[51,63,66,71,90],"ratio":[52],"of":[53],"between-subclass":[54],"scatter":[55,59],"matrix":[56],"within-subclass":[58],"matrix.":[60],"maximize":[62],"eigenvalues":[64],"along":[65],"discriminative":[67,80],"eignevector":[68],"directions.":[69],"Hence":[70],"deep":[72],"neural":[73],"network":[74],"is":[75],"able":[76],"to":[77,100],"learn":[78],"more":[79],"space":[82],"thus":[84],"has":[85],"higher":[86],"class":[87],"separation":[88],"linearly":[91],"separable":[92],"latent":[93],"space.":[94],"show":[96],"DeepSDA":[98],"leads":[99],"significant":[101],"improvements":[102],"on":[103],"diverse":[104],"categorization":[106],"attribute":[108],"benchmarks.":[110]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}