{"id":"https://openalex.org/W4375869118","doi":"https://doi.org/10.1109/icassp49357.2023.10094859","title":"ACF: Aligned Contrastive Finetuning For Language and Vision Tasks","display_name":"ACF: Aligned Contrastive Finetuning For Language and Vision Tasks","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869118","doi":"https://doi.org/10.1109/icassp49357.2023.10094859"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094859","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"https://openalex.org/A5100339289","display_name":"Wei Zhu","orcid":"https://orcid.org/0000-0002-6389-6866"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhu","raw_affiliation_strings":["East China Normal Univ,Shanghai,China","East China Normal Univ, Shanghai, China","Pingan Health Tech, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal Univ,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"East China Normal Univ, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"Pingan Health Tech, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396039","display_name":"Peng Wang","orcid":"https://orcid.org/0000-0002-5397-9115"},"institutions":[{"id":"https://openalex.org/I68986083","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908","country_code":"CN","type":"education","lineage":["https://openalex.org/I68986083"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wang","raw_affiliation_strings":["Northwestern Normal Univ,Lanzhou,China","Northwestern Normal Univ, Lanzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Normal Univ,Lanzhou,China","institution_ids":["https://openalex.org/I68986083"]},{"raw_affiliation_string":"Northwestern Normal Univ, Lanzhou, China","institution_ids":["https://openalex.org/I68986083"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100344628","display_name":"Xiaoling Wang","orcid":"https://orcid.org/0000-0002-4594-6946"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoling Wang","raw_affiliation_strings":["East China Normal Univ,Shanghai,China","East China Normal Univ, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal Univ,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"East China Normal Univ, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112109363","display_name":"Yuan Ni","orcid":"https://orcid.org/0009-0007-5406-7103"},"institutions":[{"id":"https://openalex.org/I4210161025","display_name":"Jordan Valley Semiconductors (China)","ror":"https://ror.org/05516nt33","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210149196","https://openalex.org/I4210161025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Ni","raw_affiliation_strings":["Pingan Health Tech,Shanghai,China","Pingan Health Tech, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pingan Health Tech,Shanghai,China","institution_ids":["https://openalex.org/I4210161025"]},{"raw_affiliation_string":"Pingan Health Tech, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023775139","display_name":"Guotong Xie","orcid":"https://orcid.org/0000-0002-2772-8961"},"institutions":[{"id":"https://openalex.org/I4210161025","display_name":"Jordan Valley Semiconductors (China)","ror":"https://ror.org/05516nt33","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210149196","https://openalex.org/I4210161025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guotong Xie","raw_affiliation_strings":["Pingan Health Tech,Shanghai,China","Pingan Health Tech, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pingan Health Tech,Shanghai,China","institution_ids":["https://openalex.org/I4210161025"]},{"raw_affiliation_string":"Pingan Health Tech, Shanghai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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":0.9948999881744385,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9921000003814697,"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/computer-science","display_name":"Computer science","score":0.6845223307609558}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6845223307609558}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094859","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1552847225","https://openalex.org/W2117539524","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2923014074","https://openalex.org/W2963912736","https://openalex.org/W2971092323","https://openalex.org/W2988217457","https://openalex.org/W3005680577","https://openalex.org/W3021636956","https://openalex.org/W3022104542","https://openalex.org/W3035524453","https://openalex.org/W3035542229","https://openalex.org/W3100859887","https://openalex.org/W3102725307","https://openalex.org/W3106109117","https://openalex.org/W3114651185","https://openalex.org/W3118062200","https://openalex.org/W3118608800","https://openalex.org/W3125516434","https://openalex.org/W3154229486","https://openalex.org/W3156636935","https://openalex.org/W3160913426","https://openalex.org/W3162391496","https://openalex.org/W3175362188","https://openalex.org/W3199962080","https://openalex.org/W3200253633","https://openalex.org/W4249573750","https://openalex.org/W4281384899","https://openalex.org/W4287614078","https://openalex.org/W4287812705","https://openalex.org/W4295727797","https://openalex.org/W4297808394","https://openalex.org/W6751795773","https://openalex.org/W6755207826","https://openalex.org/W6774314701","https://openalex.org/W6776700526","https://openalex.org/W6777837344","https://openalex.org/W6778102432","https://openalex.org/W6779977557","https://openalex.org/W6784874100","https://openalex.org/W6787972765","https://openalex.org/W6789642857","https://openalex.org/W6794146050"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Contrastive":[0],"learning":[1],"(CL)":[2],"has":[3],"achieved":[4],"great":[5],"success":[6],"in":[7,30,41,56,74],"various":[8],"fields":[9],"with":[10,62],"self-supervised":[11],"learning.":[12],"However,":[13],"CL":[14],"under":[15],"the":[16,27,47,63,68,75,89],"supervised":[17],"setting":[18],"is":[19,109],"not":[20],"fully":[21],"explored,":[22],"especially":[23],"how":[24],"to":[25,87],"utilize":[26],"class":[28],"labels":[29],"CL.":[31],"We":[32],"propose":[33],"a":[34,83],"novel":[35],"aligned":[36],"contrastive":[37],"finetuning":[38],"(ACF)":[39],"approach":[40],"this":[42],"work.":[43],"Specifically,":[44],"we":[45,81],"consider":[46],"label":[48,69],"embeddings":[49,70],"as":[50],"labeled":[51],"instances":[52],"and":[53,71,99,111],"put":[54],"them":[55],"an":[57],"InfoNCE":[58],"loss":[59],"objective":[60],"together":[61],"instance":[64,72],"representations,":[65],"thus":[66],"aligning":[67],"representation":[73],"same":[76],"semantic":[77],"space.":[78],"In":[79],"addition,":[80],"design":[82],"correlation-based":[84],"regularization":[85],"term":[86],"alleviate":[88],"anisotropy":[90],"problem.":[91],"Extensive":[92],"experiments":[93],"are":[94],"conducted":[95],"on":[96],"language":[97],"understanding":[98],"image":[100],"classification":[101],"tasks,":[102],"demonstrating":[103],"our":[104],"ACF":[105,108],"method\u2019s":[106],"competitiveness.":[107],"off-the-shelf":[110],"can":[112],"be":[113],"plugged":[114],"into":[115],"any":[116],"pre-trained":[117],"models":[118],"without":[119],"additional":[120],"network":[121],"architectures":[122],"or":[123],"computation":[124],"overhead.":[125]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}