{"id":"https://openalex.org/W4388553928","doi":"https://doi.org/10.48550/arxiv.2311.04157","title":"A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis","display_name":"A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis","publication_year":2023,"publication_date":"2023-11-07","ids":{"openalex":"https://openalex.org/W4388553928","doi":"https://doi.org/10.48550/arxiv.2311.04157"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2311.04157","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.04157","pdf_url":"https://arxiv.org/pdf/2311.04157","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2311.04157","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029643685","display_name":"Dipanjyoti Paul","orcid":"https://orcid.org/0000-0001-9079-7524"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Paul, Dipanjyoti","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113949305","display_name":"Arpita Chowdhury","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chowdhury, Arpita","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107459659","display_name":"Xinqi Xiong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Xinqi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102963746","display_name":"Feng-Ju Chang","orcid":"https://orcid.org/0000-0003-2405-3118"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Feng-Ju","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090386394","display_name":"David Carlyn","orcid":"https://orcid.org/0000-0002-8323-0359"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carlyn, David","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023512504","display_name":"Samuel Stevens","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stevens, Samuel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086009284","display_name":"Kaiya L. Provost","orcid":"https://orcid.org/0000-0002-5865-7238"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Provost, Kaiya L.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081622450","display_name":"Anuj Karpatne","orcid":"https://orcid.org/0000-0003-1647-3534"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karpatne, Anuj","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027836945","display_name":"Bryan C. Carstens","orcid":"https://orcid.org/0000-0002-1552-227X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carstens, Bryan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038947564","display_name":"Daniel I. Rubenstein","orcid":"https://orcid.org/0000-0001-9049-5219"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rubenstein, Daniel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035964079","display_name":"Charles V. Stewart","orcid":"https://orcid.org/0000-0001-6532-6675"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stewart, Charles","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060005215","display_name":"Tanya Berger\u2010Wolf","orcid":"https://orcid.org/0000-0001-7610-1412"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Berger-Wolf, Tanya","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108481279","display_name":"Yu Su","orcid":"https://orcid.org/0000-0003-0685-2768"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101520942","display_name":"Wei\u2010Lun Chao","orcid":"https://orcid.org/0000-0003-1269-7231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao, Wei-Lun","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":14,"corresponding_author_ids":["https://openalex.org/A5029643685"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12874","display_name":"Digital Imaging for Blood Diseases","score":0.9909999966621399,"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/T10862","display_name":"AI in cancer detection","score":0.9890999794006348,"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":0.7678253650665283},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7642117738723755},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7299108505249023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5076864957809448},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4887792766094208},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4248875379562378},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42267686128616333},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4079010486602783},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35297873616218567},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09815272688865662},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08502677083015442},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06645229458808899}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7678253650665283},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7642117738723755},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7299108505249023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5076864957809448},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4887792766094208},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4248875379562378},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42267686128616333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4079010486602783},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35297873616218567},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09815272688865662},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08502677083015442},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06645229458808899},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2311.04157","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.04157","pdf_url":"https://arxiv.org/pdf/2311.04157","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2311.04157","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.04157","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2311.04157","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.04157","pdf_url":"https://arxiv.org/pdf/2311.04157","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2334580170"],"abstract_inverted_index":{"We":[0,45,58,83,101],"present":[1],"a":[2,32,50,117,133],"novel":[3],"usage":[4],"of":[5,120,132],"Transformers":[6],"to":[7,23,27,38,68,74,94,109],"make":[8,28],"image":[9,80],"classification":[10,141],"interpretable.":[11],"Unlike":[12],"mainstream":[13],"classifiers":[14],"that":[15,103],"wait":[16],"until":[17],"the":[18,69,112,121,159],"last":[19],"fully":[20],"connected":[21],"layer":[22],"incorporate":[24],"class":[25,37,73,108],"information":[26],"predictions,":[29],"we":[30,145],"investigate":[31],"proactive":[33],"approach,":[34],"asking":[35],"each":[36,64,72,107],"search":[39],"for":[40,63,139],"itself":[41],"in":[42,78],"an":[43,79],"image.":[44],"realize":[46],"this":[47],"idea":[48],"via":[49,81,124],"Transformer":[51],"encoder-decoder":[52],"inspired":[53],"by":[54],"DEtection":[55],"TRansformer":[56,88],"(DETR).":[57],"learn":[59],"\"class-specific\"":[60],"queries":[61],"(one":[62],"class)":[65],"as":[66],"input":[67],"decoder,":[70],"enabling":[71],"localize":[75],"its":[76],"patterns":[77],"cross-attention.":[82],"name":[84],"our":[85],"approach":[86],"INterpretable":[87],"(INTR),":[89],"which":[90,144],"is":[91],"fairly":[92],"easy":[93],"implement":[95],"and":[96,142,152],"exhibits":[97],"several":[98],"compelling":[99],"properties.":[100],"show":[102],"INTR":[104,127],"intrinsically":[105],"encourages":[106],"attend":[110],"distinctively;":[111],"cross-attention":[113],"weights":[114],"thus":[115],"provide":[116],"faithful":[118],"interpretation":[119],"prediction.":[122],"Interestingly,":[123],"\"multi-head\"":[125],"cross-attention,":[126],"could":[128],"identify":[129],"different":[130],"\"attributes\"":[131],"class,":[134],"making":[135],"it":[136],"particularly":[137],"suitable":[138],"fine-grained":[140],"analysis,":[143],"demonstrate":[146],"on":[147],"eight":[148],"datasets.":[149],"Our":[150],"code":[151],"pre-trained":[153],"models":[154],"are":[155],"publicly":[156],"accessible":[157],"at":[158],"Imageomics":[160],"Institute":[161],"GitHub":[162],"site:":[163],"https://github.com/Imageomics/INTR.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2023-11-10T00:00:00"}