{"id":"https://openalex.org/W4392909670","doi":"https://doi.org/10.1109/icassp48485.2024.10447673","title":"ProAug: Prototype-Based Augmentation for Long-Tailed Image Classification","display_name":"ProAug: Prototype-Based Augmentation for Long-Tailed Image Classification","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909670","doi":"https://doi.org/10.1109/icassp48485.2024.10447673"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447673","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":null,"display_name":"Yan Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Hong","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395004","display_name":"Jianfu Zhang","orcid":"https://orcid.org/0000-0002-2673-5860"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfu Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073661044","display_name":"Zhongyi Sun","orcid":"https://orcid.org/0000-0002-2466-283X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyi Sun","raw_affiliation_strings":["Tencent,Youtu Lab","Youtu Lab, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Youtu Lab, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101967246","display_name":"Ke Yan","orcid":"https://orcid.org/0000-0003-3424-4866"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Yan","raw_affiliation_strings":["Tencent,Youtu Lab","Youtu Lab, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Youtu Lab, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5273,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84476718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3035","last_page":"3039"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.710099995136261,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.710099995136261,"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":0.6481999754905701,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.580299973487854,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"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/computer-science","display_name":"Computer science","score":0.7089982628822327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5440539121627808},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4368918538093567},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3943471908569336},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3705763518810272}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7089982628822327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5440539121627808},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4368918538093567},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3943471908569336},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3705763518810272}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447673","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2797977484","https://openalex.org/W2962895364","https://openalex.org/W2962933664","https://openalex.org/W2963351448","https://openalex.org/W2963845150","https://openalex.org/W3034601242","https://openalex.org/W3034711780","https://openalex.org/W3035730922","https://openalex.org/W3080359291","https://openalex.org/W3096688134","https://openalex.org/W3118608800","https://openalex.org/W3126272270","https://openalex.org/W3128945844","https://openalex.org/W3158299003","https://openalex.org/W3166596953","https://openalex.org/W3177200443","https://openalex.org/W3177230409","https://openalex.org/W3215720729","https://openalex.org/W4214519401","https://openalex.org/W4312281439","https://openalex.org/W4312866014","https://openalex.org/W4375839990","https://openalex.org/W6750523955","https://openalex.org/W6763430915","https://openalex.org/W6764733053","https://openalex.org/W6768920361","https://openalex.org/W6784097300","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Real-world":[0],"data":[1,33],"often":[2],"exhibit":[3],"long-tailed":[4],"distributions":[5],"with":[6,62,92],"heavy":[7],"class":[8],"imbalance,":[9],"which":[10],"deteriorates":[11],"the":[12,16,32,38,76,100,105,134],"generalization":[13],"performance":[14],"of":[15,47,102,107,119,136],"classifier.":[17],"To":[18],"mitigate":[19],"this":[20],"problem,":[21],"we":[22,80],"propose":[23],"a":[24,48,53,110],"novel":[25],"Prototype-based":[26],"Augmentation":[27],"framework":[28],"(ProAug)":[29],"to":[30,66,82,97,115,121],"address":[31],"scarcity":[34],"issue":[35],"by":[36,87],"augmenting":[37],"feature":[39],"space":[40],"for":[41,72],"tail":[42],"classes.":[43],"Our":[44],"ProAug":[45,120],"consists":[46],"prototype":[49],"construction":[50],"branch":[51],"and":[52,69,104,130],"dynamic":[54,77],"augmentation":[55,78],"branch.":[56],"The":[57],"prototype-based":[58],"dictionary":[59],"is":[60,113],"optimized":[61],"category-aware":[63],"margin":[64],"loss":[65],"learn":[67],"multi-center":[68],"discriminative":[70],"prototypes":[71,91,103],"each":[73],"category.":[74],"In":[75],"branch,":[79],"aim":[81],"produce":[83],"high-quality":[84],"tail-class":[85],"features":[86],"dynamically":[88],"composing":[89],"context-similar":[90],"an":[93],"attention":[94],"mechanism.":[95],"Moreover,":[96],"further":[98],"improve":[99],"reliability":[101],"quality":[106],"augmented":[108],"features,":[109],"meta-update":[111],"strategy":[112],"adopted":[114],"calibrate":[116],"two":[117],"branches":[118],"boost":[122],"performance.":[123],"Extensive":[124],"empirical":[125],"results":[126],"on":[127],"CIFAR-LT-10/100,":[128],"ImageNet-LT,":[129],"iNaturalist":[131],"2018":[132],"demonstrate":[133],"effectiveness":[135],"our":[137],"method.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}