{"id":"https://openalex.org/W4408356797","doi":"https://doi.org/10.1109/icassp49660.2025.10890753","title":"Prototypical Part Transformer for Interpretable Image Recognition","display_name":"Prototypical Part Transformer for Interpretable Image Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356797","doi":"https://doi.org/10.1109/icassp49660.2025.10890753"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5020912571","display_name":"Anni Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anni Yu","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111673780","display_name":"Yu-Bin Yang","orcid":"https://orcid.org/0000-0002-3764-1114"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Bin Yang","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02800402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.8432999849319458,"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/T10320","display_name":"Neural Networks and Applications","score":0.8432999849319458,"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":0.6351815462112427},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5741252303123474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5622891783714294},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4478892385959625},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43108171224594116},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17120146751403809},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09391406178474426},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07780236005783081}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6351815462112427},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5741252303123474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5622891783714294},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4478892385959625},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43108171224594116},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17120146751403809},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09391406178474426},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07780236005783081}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2019790506","https://openalex.org/W2138011018","https://openalex.org/W3035422918","https://openalex.org/W3094502228","https://openalex.org/W3138516171","https://openalex.org/W3158278463","https://openalex.org/W3167738759","https://openalex.org/W3176196997","https://openalex.org/W3202183072","https://openalex.org/W3202988816","https://openalex.org/W3215928733","https://openalex.org/W4214634256","https://openalex.org/W4313194958","https://openalex.org/W4385245566","https://openalex.org/W4386065251","https://openalex.org/W4390872821","https://openalex.org/W4390874420","https://openalex.org/W4393146351","https://openalex.org/W4401023994","https://openalex.org/W6638319203","https://openalex.org/W6753001334","https://openalex.org/W6765638835","https://openalex.org/W6781630272","https://openalex.org/W6788135285","https://openalex.org/W6795475546","https://openalex.org/W6810308849","https://openalex.org/W6857802407","https://openalex.org/W6859049075","https://openalex.org/W6861354353"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","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":{"Prototypical":[0,65],"Part":[1,66],"Networks":[2,28],"facilitate":[3],"interpretable":[4,70],"decision-making":[5],"processes,":[6],"with":[7,57],"the":[8,51,58,86,93],"classification":[9],"score":[10],"computed":[11],"by":[12,79,98],"comparing":[13],"test":[14],"image":[15],"patches":[16],"to":[17,73,113],"learned":[18],"prototypes.":[19],"Existing":[20],"work":[21],"typically":[22],"learns":[23],"prototypes":[24],"from":[25],"Convolutional":[26],"Neural":[27],"(CNNs).":[29],"However,":[30],"learning":[31,76,127],"prototypical":[32,82,126],"parts":[33],"directly":[34],"in":[35,40,77],"Vision":[36],"Transformers":[37],"(ViTs)":[38],"results":[39],"fragmented":[41],"and":[42,105,116,129,136],"noisy":[43],"prototype":[44,75,94,101],"activations.":[45],"To":[46],"address":[47],"this,":[48],"we":[49,63],"quantify":[50],"dispersion":[52],"of":[53],"prototypes\u2019":[54],"responsive":[55],"regions":[56],"Diffusion":[59],"Index":[60],"(DI).":[61],"Subsequently,":[62],"propose":[64],"Transformer":[67],"(PPTformer),":[68],"an":[69],"model":[71],"designed":[72],"refine":[74],"ViTs":[78],"introducing":[80],"distinct":[81],"branches,":[83],"either":[84],"involving":[85],"CLS":[87],"token":[88],"or":[89],"not.":[90],"In":[91],"PPTformer,":[92],"space":[95],"is":[96,111],"defined":[97],"orthogonal":[99],"class-aware":[100],"vectors,":[102],"ensuring":[103],"disentanglement":[104],"informativeness.":[106],"Additionally,":[107],"classaware":[108],"activation":[109],"refinement":[110],"introduced":[112],"focus":[114],"attention":[115],"reduce":[117],"DI.":[118],"Extensive":[119],"experiments":[120],"demonstrate":[121],"that":[122],"PPTformer":[123],"outperforms":[124],"state-of-the-art":[125],"methods":[128],"its":[130],"non-interpretable":[131],"counterparts,":[132],"providing":[133],"faithful":[134],"local":[135],"global":[137],"explanations.":[138]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}