{"id":"https://openalex.org/W4415540289","doi":"https://doi.org/10.1145/3746027.3755129","title":"Fourier Self-Adaptation for Transferring General Pretrained Models to Specific Domains","display_name":"Fourier Self-Adaptation for Transferring General Pretrained Models to Specific Domains","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540289","doi":"https://doi.org/10.1145/3746027.3755129"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755129","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Lei Liu","orcid":"https://orcid.org/0009-0006-0962-724X"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Liu","raw_affiliation_strings":["Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0009-0006-0962-724X","affiliations":[{"raw_affiliation_string":"Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010464164","display_name":"Xiangdong Su","orcid":"https://orcid.org/0000-0001-8061-1474"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangdong Su","raw_affiliation_strings":["Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0000-0001-8061-1474","affiliations":[{"raw_affiliation_string":"Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0009-0005-5513-1192","affiliations":[{"raw_affiliation_string":"Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"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":"3605","last_page":"3614"},"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":0.9830999970436096,"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":0.9830999970436096,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9769999980926514,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9567000269889832,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6848000288009644},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6194000244140625},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.5702000260353088},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.5303000211715698},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.45820000767707825},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.453000009059906},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4503999948501587},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43619999289512634},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4146000146865845}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6848000288009644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6823999881744385},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6194000244140625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5932999849319458},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.5702000260353088},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.5303000211715698},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.45820000767707825},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.453000009059906},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4503999948501587},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43619999289512634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4146000146865845},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4120999872684479},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4002000093460083},{"id":"https://openalex.org/C125245961","wikidata":"https://www.wikidata.org/wiki/Q221656","display_name":"Brightness","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C3019555358","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Fourier domain","level":3,"score":0.3808000087738037},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.37279999256134033},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C207864730","wikidata":"https://www.wikidata.org/wiki/Q179467","display_name":"Fourier series","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.3075000047683716},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2727999985218048},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.25519999861717224},{"id":"https://openalex.org/C171836373","wikidata":"https://www.wikidata.org/wiki/Q2266329","display_name":"Linear interpolation","level":3,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755129","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3050513244","display_name":null,"funder_award_id":"Grant No. 62366036","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1966382373","https://openalex.org/W1980038761","https://openalex.org/W2194775991","https://openalex.org/W2326925005","https://openalex.org/W2515866431","https://openalex.org/W2592962403","https://openalex.org/W2745461083","https://openalex.org/W2760432156","https://openalex.org/W2963954913","https://openalex.org/W2980113592","https://openalex.org/W3035294798","https://openalex.org/W3035682985","https://openalex.org/W3127724266","https://openalex.org/W3138516171","https://openalex.org/W3164670515","https://openalex.org/W3169044395","https://openalex.org/W3183864931","https://openalex.org/W3203255640","https://openalex.org/W4313156423","https://openalex.org/W4379878309"],"related_works":[],"abstract_inverted_index":{"While":[0],"pre-trained":[1,188,234],"models":[2,14,47,189],"in":[3],"the":[4,58,96,112,115,122,126,139,146,151,163,171,175],"general":[5,46,187],"domain":[6,22,78,92,117,177],"have":[7],"proliferated,":[8],"existing":[9],"methods":[10],"for":[11,24,31],"transferring":[12],"these":[13],"to":[15,48,168,229,232],"specific":[16,53,204],"domains":[17,205],"often":[18],"depend":[19],"on":[20,170,190],"source":[21,37],"data":[23,152,178],"distribution":[25,98,153],"alignment":[26],"and":[27,64,70,84,135,149,196,212],"are":[28,238],"typically":[29],"tailored":[30],"single":[32],"tasks.":[33],"We":[34,183],"propose":[35],"a":[36,49,101,106,158],"data-free":[38],"approach,":[39],"Fourier":[40,62],"Self-Adaptation":[41],"(FSA),":[42],"which":[43,73,87],"effectively":[44],"adapts":[45],"wide":[50],"range":[51],"of":[52,61,114,121,145,174],"domains.":[54],"Our":[55,214],"method":[56,215],"leverages":[57],"distinct":[59],"properties":[60],"phase":[63,66,143],"amplitude:":[65],"contains":[67,82],"high-level":[68],"structural":[69],"positional":[71],"information,":[72,86],"is":[74,88,129],"less":[75],"affected":[76,90],"by":[77,91,99,132],"shifts,":[79],"while":[80,179],"amplitude":[81,113,155],"details":[83],"brightness":[85],"more":[89],"shifts.":[93],"FSA":[94,185],"adjusts":[95],"image":[97,104,118,148,193],"initializing":[100],"trainable":[102],"adaptive":[103,123],"from":[105,227],"normal":[107],"distribution.":[108],"It":[109],"then":[110],"interpolates":[111],"target":[116,147,176],"with":[119,223],"that":[120],"image,":[124],"where":[125],"interpolation":[127],"ratio":[128],"dynamically":[130],"controlled":[131],"learnable":[133],"weight":[134],"bias.":[136],"During":[137],"training,":[138],"model":[140,164],"captures":[141],"advanced":[142],"information":[144],"refines":[150],"through":[154],"interpolation.":[156],"Additionally,":[157],"dual":[159],"regularization":[160],"loss":[161],"constrains":[162],"representation,":[165],"encouraging":[166],"it":[167],"focus":[169],"intrinsic":[172],"relationships":[173],"discarding":[180],"irrelevant":[181],"knowledge.":[182],"evaluate":[184],"using":[186],"11":[191],"unimodal":[192],"classification":[194],"datasets":[195],"6":[197],"multimodal":[198],"visual":[199],"question":[200],"answering":[201],"datasets,":[202,222],"covering":[203],"such":[206],"as":[207],"radiology,":[208],"pathology,":[209],"remote":[210],"sensing,":[211],"art.":[213],"consistently":[216],"achieves":[217],"state-of-the-art":[218],"performance":[219,224],"across":[220],"multiple":[221],"improvements":[225],"ranging":[226],"1%":[228],"8%":[230],"compared":[231],"basic":[233],"models.":[235],"Source":[236],"code":[237],"available":[239],"at":[240],"https://github.com/Alivelei/FSA.":[241]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}