{"id":"https://openalex.org/W4319300584","doi":"https://doi.org/10.1109/wacv56688.2023.00414","title":"Center-aware Adversarial Augmentation for Single Domain Generalization","display_name":"Center-aware Adversarial Augmentation for Single Domain Generalization","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4319300584","doi":"https://doi.org/10.1109/wacv56688.2023.00414"},"language":"en","primary_location":{"id":"doi:10.1109/wacv56688.2023.00414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv56688.2023.00414","pdf_url":null,"source":{"id":"https://openalex.org/S4363607736","display_name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/handle/20.500.14299/199450","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088531741","display_name":"Tianle Chen","orcid":"https://orcid.org/0009-0000-5930-0145"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianle Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014648528","display_name":"Mahsa Baktashmotlagh","orcid":"https://orcid.org/0000-0001-5255-8194"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mahsa Baktashmotlagh","raw_affiliation_strings":["The University of Queensland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Queensland","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371707","display_name":"Zijian Wang","orcid":"https://orcid.org/0000-0002-7190-9620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zijian Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5049300388","display_name":"Mathieu Salzmann","orcid":"https://orcid.org/0000-0002-8347-8637"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mathieu Salzmann","raw_affiliation_strings":["EPFL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPFL","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8803,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.97084062,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4146","last_page":"4154"},"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":0.9986000061035156,"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":0.9986000061035156,"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/T12169","display_name":"Non-Destructive Testing Techniques","score":0.9509000182151794,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7843056321144104},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7620479464530945},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6954816579818726},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6761857271194458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5742098689079285},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4924076795578003},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4919593036174774},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.47596973180770874},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47540387511253357},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4427122473716736},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11198493838310242}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7843056321144104},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7620479464530945},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6954816579818726},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6761857271194458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5742098689079285},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4924076795578003},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4919593036174774},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.47596973180770874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47540387511253357},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4427122473716736},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11198493838310242},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wacv56688.2023.00414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv56688.2023.00414","pdf_url":null,"source":{"id":"https://openalex.org/S4363607736","display_name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:303885","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/199450","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WoS","raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:303885","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/199450","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WoS","raw_type":"conference proceedings"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W648260396","https://openalex.org/W1583837637","https://openalex.org/W2064447488","https://openalex.org/W2100659887","https://openalex.org/W2147800946","https://openalex.org/W2187089797","https://openalex.org/W2295107390","https://openalex.org/W2335728318","https://openalex.org/W2514499445","https://openalex.org/W2520774990","https://openalex.org/W2763549966","https://openalex.org/W2795155917","https://openalex.org/W2806187986","https://openalex.org/W2889945482","https://openalex.org/W2947707615","https://openalex.org/W2958360136","https://openalex.org/W2963118547","https://openalex.org/W2963327260","https://openalex.org/W2964137095","https://openalex.org/W3009454144","https://openalex.org/W3010293082","https://openalex.org/W3034373371","https://openalex.org/W3038585207","https://openalex.org/W3041340781","https://openalex.org/W3092753908","https://openalex.org/W3128475431","https://openalex.org/W3172854222","https://openalex.org/W3174099230","https://openalex.org/W4214480085","https://openalex.org/W4229482837","https://openalex.org/W4288404646","https://openalex.org/W4301599248","https://openalex.org/W6677645113","https://openalex.org/W6683124652","https://openalex.org/W6725739970","https://openalex.org/W6750109254","https://openalex.org/W6752160200","https://openalex.org/W6757555829","https://openalex.org/W6763101577","https://openalex.org/W6763468762","https://openalex.org/W6780061525","https://openalex.org/W6780170441","https://openalex.org/W6781506369","https://openalex.org/W6784146242","https://openalex.org/W6787972765","https://openalex.org/W6792568423"],"related_works":["https://openalex.org/W3211393740","https://openalex.org/W3208049411","https://openalex.org/W3022908591","https://openalex.org/W2946768379","https://openalex.org/W2981877337","https://openalex.org/W3101081936","https://openalex.org/W3203938600","https://openalex.org/W4286910063","https://openalex.org/W2163707935","https://openalex.org/W83146503"],"abstract_inverted_index":{"Domain":[0],"generalization":[1,32,118],"(DG)":[2],"aims":[3],"to":[4,18,37,68,83,87,98,109,142,160],"learn":[5],"a":[6,27,39,111,125,151],"model":[7],"from":[8,26,146],"multiple":[9],"training":[10,53],"(i.e.,":[11,22],"source)":[12],"domains":[13],"that":[14,130,175],"can":[15],"generalize":[16],"well":[17],"the":[19,70,89,95,101,132,137,147,162,179],"unseen":[20],"test":[21],"target)":[23],"data":[24,63,74],"coming":[25],"different":[28],"distribution.":[29],"Single":[30],"domain":[31,49,113],"(Single-DG)":[33],"has":[34],"recently":[35],"emerged":[36],"tackle":[38],"more":[40],"challenging,":[41],"yet":[42],"realistic":[43],"setting,":[44],"where":[45],"only":[46],"one":[47],"source":[48,73,133,138],"is":[50],"available":[51],"at":[52],"time.":[54],"The":[55],"existing":[56],"Single-DG":[57,172],"approaches":[58],"typically":[59,105],"are":[60,104],"based":[61],"on":[62,167],"augmentation":[64,128],"strategies":[65],"and":[66,173],"aim":[67,82],"expand":[69],"span":[71],"of":[72,164],"by":[75,135],"augmenting":[76],"out-of-domain":[77],"samples.":[78],"Generally":[79],"speaking,":[80],"they":[81],"generate":[84],"hard":[85],"examples":[86],"confuse":[88],"classifier.":[90],"While":[91],"this":[92],"may":[93],"make":[94],"classifier":[96],"robust":[97],"small":[99],"perturbation,":[100],"generated":[102],"samples":[103,139],"not":[106],"diverse":[107],"enough":[108],"mimic":[110],"large":[112],"shift,":[114],"resulting":[115],"in":[116,181],"sub-optimal":[117],"performance.":[119],"To":[120],"alleviate":[121],"this,":[122],"we":[123],"propose":[124],"center-aware":[126],"adversarial":[127],"technique":[129],"expands":[131],"distribution":[134],"altering":[136],"so":[140],"as":[141],"push":[143],"them":[144],"away":[145],"class":[148],"centers":[149],"via":[150],"novel":[152],"angular":[153],"center":[154],"loss.":[155],"We":[156],"conduct":[157],"extensive":[158],"experiments":[159],"demonstrate":[161],"effectiveness":[163],"our":[165,176],"approach":[166],"several":[168],"benchmark":[169],"datasets":[170],"for":[171],"show":[174],"method":[177],"outperforms":[178],"state-of-the-art":[180],"most":[182],"cases.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}