{"id":"https://openalex.org/W4387968581","doi":"https://doi.org/10.1145/3581783.3612234","title":"Consistency-aware Feature Learning for Hierarchical Fine-grained Visual Classification","display_name":"Consistency-aware Feature Learning for Hierarchical Fine-grained Visual Classification","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968581","doi":"https://doi.org/10.1145/3581783.3612234"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612234","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612234","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612234","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612234","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100431257","display_name":"Rui Wang","orcid":"https://orcid.org/0000-0002-4792-1945"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["SKLOIS, Institute of Information Engineering, CAS;School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","SKLOIS, Institute of Information Engineering, CAS"],"raw_orcid":"https://orcid.org/0000-0002-4792-1945","affiliations":[{"raw_affiliation_string":"SKLOIS, Institute of Information Engineering, CAS;School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"SKLOIS, Institute of Information Engineering, CAS","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066214523","display_name":"C.L. Zou","orcid":"https://orcid.org/0000-0002-1901-5363"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Zou","raw_affiliation_strings":["SKLOIS, Institute of Information Engineering, CAS;School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","SKLOIS, Institute of Information Engineering, CAS"],"raw_orcid":"https://orcid.org/0000-0002-1901-5363","affiliations":[{"raw_affiliation_string":"SKLOIS, Institute of Information Engineering, CAS;School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"SKLOIS, Institute of Information Engineering, CAS","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693727","display_name":"Weizhong Zhang","orcid":"https://orcid.org/0000-0001-7311-0698"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weizhong Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7311-0698","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102922399","display_name":"Zixuan Zhu","orcid":"https://orcid.org/0009-0003-0678-3405"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixuan Zhu","raw_affiliation_strings":["SKLOIS, Institute of Information Engineering, CAS;School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","SKLOIS, Institute of Information Engineering, CAS"],"raw_orcid":"https://orcid.org/0009-0003-0678-3405","affiliations":[{"raw_affiliation_string":"SKLOIS, Institute of Information Engineering, CAS;School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"SKLOIS, Institute of Information Engineering, CAS","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013812973","display_name":"Lihua Jing","orcid":"https://orcid.org/0009-0005-6369-7890"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihua Jing","raw_affiliation_strings":["SKLOIS, Institute of Information Engineering, CAS;School of Cyber Security, University of Chinese Academy of Sciences, NEED, China","SKLOIS, Institute of Information Engineering, CAS"],"raw_orcid":"https://orcid.org/0009-0005-6369-7890","affiliations":[{"raw_affiliation_string":"SKLOIS, Institute of Information Engineering, CAS;School of Cyber Security, University of Chinese Academy of Sciences, NEED, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"SKLOIS, Institute of Information Engineering, CAS","institution_ids":["https://openalex.org/I4210156404"]}]}],"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":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2326","last_page":"2334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9991999864578247,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9955999851226807,"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/computer-science","display_name":"Computer science","score":0.7736274600028992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6889936327934265},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6376477479934692},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5599721074104309},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5555826425552368},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.45768868923187256},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.443612664937973},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4378371238708496},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4341965317726135},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.425807386636734}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7736274600028992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6889936327934265},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6376477479934692},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5599721074104309},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5555826425552368},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.45768868923187256},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.443612664937973},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4378371238708496},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4341965317726135},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.425807386636734},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3612234","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612234","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612234","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-158230","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-158230","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612234","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612234","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612234","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G34267490","display_name":null,"funder_award_id":"62176253","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5566207747","display_name":null,"funder_award_id":"U20B2066","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387968581.pdf","grobid_xml":"https://content.openalex.org/works/W4387968581.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W56385144","https://openalex.org/W1898560071","https://openalex.org/W1955942245","https://openalex.org/W2124396699","https://openalex.org/W2138011018","https://openalex.org/W2295107390","https://openalex.org/W2520368209","https://openalex.org/W2554320282","https://openalex.org/W2560674852","https://openalex.org/W2740620254","https://openalex.org/W2752782242","https://openalex.org/W2761785940","https://openalex.org/W2773003563","https://openalex.org/W2780838211","https://openalex.org/W2798365843","https://openalex.org/W2807931652","https://openalex.org/W2885613075","https://openalex.org/W2955058313","https://openalex.org/W2963066927","https://openalex.org/W2963407932","https://openalex.org/W2963677766","https://openalex.org/W2963691377","https://openalex.org/W2963877604","https://openalex.org/W2966182616","https://openalex.org/W3010121230","https://openalex.org/W3082811686","https://openalex.org/W3097217077","https://openalex.org/W3166091781","https://openalex.org/W3172917901","https://openalex.org/W3205604798","https://openalex.org/W3206567833","https://openalex.org/W3206734547","https://openalex.org/W3209861566","https://openalex.org/W4210551401","https://openalex.org/W4312349930","https://openalex.org/W4312696925"],"related_works":["https://openalex.org/W1496222301","https://openalex.org/W3207760230","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703","https://openalex.org/W41015297","https://openalex.org/W4280645561"],"abstract_inverted_index":{"Hierarchical":[0],"Fine-Grained":[1],"Visual":[2],"Classification":[3],"(HFGVC)":[4],"assigns":[5],"a":[6,14,84,101],"label":[7,96],"sequence":[8],"(e.g.,":[9],"[\"Albatross'',":[10],"\"Laysan":[11],"Albatross''])":[12],"with":[13,119],"coarse":[15],"to":[16,19,25,32,65,77,108,130],"fine":[17],"hierarchy":[18],"each":[20,128],"object.":[21],"It":[22],"remains":[23],"challenging":[24],"achieve":[26],"high":[27],"accuracy":[28,71,175],"and":[29,40,69,91,103,123,161],"consistency":[30,68,81],"due":[31],"the":[33,79,95,110,113,120,132,135,185],"small":[34],"inter-class":[35],"difference,":[36],"large":[37],"intra-class":[38],"variance,":[39],"difficulty":[41],"in":[42,146],"modeling":[43],"relationships":[44],"among":[45],"classification":[46,70,106,174,188],"tasks":[47],"at":[48,115,137],"different":[49,116],"granularities.":[50,117],"In":[51],"this":[52],"paper,":[53],"we":[54,99],"propose":[55],"an":[56],"effective":[57],"Consistency-Aware":[58],"Feature":[59],"Learning":[60],"(CAFL)":[61],"method":[62,151,169],"for":[63,112],"HFGVC":[64],"improve":[66],"prediction":[67,80],"simultaneously.":[72],"Our":[73],"key":[74],"idea":[75],"is":[76],"encode":[78],"constraint":[82],"into":[83],"weak":[85],"supervision":[86],"mechanism":[87],"via":[88],"forward":[89],"deduction":[90],"backward":[92],"induction":[93],"over":[94],"hierarchy.":[97],"Furthermore,":[98],"develop":[100],"disentanglement":[102],"bidirectional":[104],"reinforcement":[105],"head":[107],"extract":[109],"features":[111,133],"classifiers":[114],"Together":[118],"stop-gradient":[121],"policy":[122],"attention":[124],"mechanism,":[125],"they":[126],"enable":[127],"classifier":[129],"exploit":[131],"from":[134,142],"ones":[136],"other":[138],"granularities":[139],"without":[140],"suffering":[141],"their":[143],"conflicting":[144],"gradients":[145],"training.":[147],"We":[148],"evaluate":[149],"our":[150,168],"on":[152],"several":[153],"commonly-used":[154],"fine-grained":[155,187],"public":[156],"datasets,":[157],"including":[158],"CUB-200-2011,":[159],"FGVC-Aircraft,":[160],"Stanford":[162],"Cars.":[163],"The":[164],"results":[165],"show":[166],"that":[167],"not":[170],"only":[171],"achieves":[172],"state-of-the-art":[173],"but":[176],"also":[177],"effectively":[178],"reduces":[179],"inconsistency":[180],"errors":[181],"by":[182],"50%":[183],"under":[184],"hierarchical":[186],"setting.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}