{"id":"https://openalex.org/W3210482797","doi":"https://doi.org/10.1109/icsipa52582.2021.9576812","title":"Unified Discriminant and Distribution Alignment for Visual Domain Adaptation","display_name":"Unified Discriminant and Distribution Alignment for Visual Domain Adaptation","publication_year":2021,"publication_date":"2021-09-13","ids":{"openalex":"https://openalex.org/W3210482797","doi":"https://doi.org/10.1109/icsipa52582.2021.9576812","mag":"3210482797"},"language":"en","primary_location":{"id":"doi:10.1109/icsipa52582.2021.9576812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsipa52582.2021.9576812","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 Signal and Image Processing Applications (ICSIPA)","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/A5090885239","display_name":"M. S. Rizal Samsudin","orcid":"https://orcid.org/0000-0003-1215-1335"},"institutions":[{"id":"https://openalex.org/I4576418","display_name":"University of Technology Malaysia","ror":"https://ror.org/026w31v75","country_code":"MY","type":"education","lineage":["https://openalex.org/I4576418"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"M. S. Rizal Samsudin","raw_affiliation_strings":["CVVIP Lab, School of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru, Malaysia"],"affiliations":[{"raw_affiliation_string":"CVVIP Lab, School of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru, Malaysia","institution_ids":["https://openalex.org/I4576418"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Syed A.R. Abu Bakar","orcid":null},"institutions":[{"id":"https://openalex.org/I4576418","display_name":"University of Technology Malaysia","ror":"https://ror.org/026w31v75","country_code":"MY","type":"education","lineage":["https://openalex.org/I4576418"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Syed A.R. Abu Bakar","raw_affiliation_strings":["CVVIP Lab, School of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru, Malaysia"],"affiliations":[{"raw_affiliation_string":"CVVIP Lab, School of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru, Malaysia","institution_ids":["https://openalex.org/I4576418"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083191333","display_name":"Musa Mohd Mokji","orcid":"https://orcid.org/0000-0002-7590-8481"},"institutions":[{"id":"https://openalex.org/I4576418","display_name":"University of Technology Malaysia","ror":"https://ror.org/026w31v75","country_code":"MY","type":"education","lineage":["https://openalex.org/I4576418"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Musa Mohd Mokji","raw_affiliation_strings":["CVVIP Lab, School of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru, Malaysia"],"affiliations":[{"raw_affiliation_string":"CVVIP Lab, School of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru, Malaysia","institution_ids":["https://openalex.org/I4576418"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5090885239"],"corresponding_institution_ids":["https://openalex.org/I4576418"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1625715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":null,"first_page":"209","last_page":"214"},"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":0.9998000264167786,"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":0.9998000264167786,"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/T12676","display_name":"Machine Learning and ELM","score":0.9437999725341797,"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/T10981","display_name":"Cytomegalovirus and herpesvirus research","score":0.9024999737739563,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7359957098960876},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.7079602479934692},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6814991235733032},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6343632936477661},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.5468981266021729},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.5430911779403687},{"id":"https://openalex.org/keywords/discriminant","display_name":"Discriminant","score":0.5144834518432617},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3966148793697357}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7359957098960876},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.7079602479934692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6814991235733032},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6343632936477661},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.5468981266021729},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.5430911779403687},{"id":"https://openalex.org/C78397625","wikidata":"https://www.wikidata.org/wiki/Q192487","display_name":"Discriminant","level":2,"score":0.5144834518432617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3966148793697357}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsipa52582.2021.9576812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsipa52582.2021.9576812","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 Signal and Image Processing Applications (ICSIPA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.699999988079071,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W191001584","https://openalex.org/W1722318740","https://openalex.org/W2057266281","https://openalex.org/W2096943734","https://openalex.org/W2100659887","https://openalex.org/W2104290444","https://openalex.org/W2112796928","https://openalex.org/W2115403315","https://openalex.org/W2149466042","https://openalex.org/W2154872931","https://openalex.org/W2329664094","https://openalex.org/W2616287544","https://openalex.org/W2783376202","https://openalex.org/W2790688554","https://openalex.org/W2791052411","https://openalex.org/W2884771968","https://openalex.org/W2935033494","https://openalex.org/W2963693396","https://openalex.org/W2963756240","https://openalex.org/W2964575823","https://openalex.org/W2997701990","https://openalex.org/W3041133507","https://openalex.org/W3090414386","https://openalex.org/W4302286858","https://openalex.org/W6637542466","https://openalex.org/W6675747103","https://openalex.org/W6681637710","https://openalex.org/W6682644385","https://openalex.org/W6761507452"],"related_works":["https://openalex.org/W2350751952","https://openalex.org/W2362114017","https://openalex.org/W1999647744","https://openalex.org/W2794812819","https://openalex.org/W2114217318","https://openalex.org/W3147024994","https://openalex.org/W1978302214","https://openalex.org/W2587881214","https://openalex.org/W3104072235","https://openalex.org/W2374055396"],"abstract_inverted_index":{"In":[0,196],"visual":[1],"understandings,":[2],"images":[3],"taken":[4],"from":[5,50],"different":[6,10],"cameras":[7],"usually":[8],"have":[9],"resolutions,":[11],"illumination,":[12],"poses,":[13],"and":[14,44,54,79,110,128,137,151,156,189,200,206,211,234,247,253],"background":[15],"views":[16],"that":[17,146,185],"lead":[18,32],"to":[19,33,100,131,149,169,174],"domain":[20,38,70,118,221],"shift.":[21],"Besides":[22],"labeling":[23],"these":[24],"data":[25,46],"is":[26,147,168],"an":[27,66],"expensive":[28],"operation.":[29],"These":[30],"problems":[31],"the":[34,51,60,93,101,113,116,133,175,187,193,219,225,229,242,251],"need":[35],"for":[36,68],"unsupervised":[37,69,90],"adaptation":[39,71,222],"(UDA),":[40],"in":[41,59,72,115,153,160,192,232],"which":[42],"training":[43],"testing":[45],"are":[47,56],"not":[48,57],"drawn":[49],"same":[52],"distribution,":[53],"labels":[55],"available":[58],"target":[61],"domain.":[62,195],"This":[63],"paper":[64,167],"presents":[65],"improvement":[67],"transfer":[73],"learning":[74],"using":[75],"a":[76],"unified":[77],"discriminant":[78,172,182,191],"distribution":[80,107],"alignment":[81],"(UDDA).":[82],"The":[83,163],"existing":[84],"method":[85,135,227],"of":[86,106,165],"UDA":[87,177],"only":[88,157],"utilized":[89,121],"PCA":[91],"as":[92],"dimensionality":[94],"reduction":[95],"process":[96],"before":[97,215],"being":[98,216],"added":[99],"joint":[102,126,220],"objective":[103],"function":[104],"consisting":[105],"discrepancy":[108],"minimization":[109],"regularization.":[111],"However,":[112],"label":[114],"source":[117,194],"has":[119,143],"been":[120],"by":[122,179,245],"some":[123,144],"works":[124],"(i.e.,":[125],"geometrical":[127],"statistical":[129],"(JGSA))":[130],"use":[132],"supervised":[134],"LDA":[136,142],"show":[138],"good":[139],"improvement.":[140],"Nevertheless,":[141],"drawbacks":[145],"sensitive":[148],"noise":[150],"outlier":[152],"square":[154],"operations":[155],"take":[158],"part":[159],"global":[161],"information.":[162],"contribution":[164],"this":[166,197],"add":[170],"local":[171],"information":[173],"proposed":[176,226],"model":[178],"adopting":[180],"locality-sensitive":[181],"analysis":[183],"(LSDA)":[184],"strengthens":[186],"between-class":[188,201,212],"within-class":[190,199,210],"method,":[198],"graphs":[202],"will":[203],"be":[204],"computed,":[205],"summed":[207],"up":[208],"with":[209,228,250],"scatter":[213],"matrices":[214],"embedded":[217],"into":[218],"framework.":[223],"Comparing":[224],"state-of-the-art":[230],"techniques":[231],"objects":[233],"digital":[235],"datasets,":[236],"it":[237],"shows":[238],"our":[239],"UDDA":[240],"improved":[241],"average":[243],"accuracy":[244],"3.43%":[246],"7.13%":[248],"compare":[249],"second":[252],"third":[254],"highest":[255],"results":[256],"respectively.":[257]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}