{"id":"https://openalex.org/W4408345910","doi":"https://doi.org/10.1109/icassp49660.2025.10889617","title":"MedFocusCLIP: Improving few shot classification in medical datasets using pixel wise attention","display_name":"MedFocusCLIP: Improving few shot classification in medical datasets using pixel wise attention","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345910","doi":"https://doi.org/10.1109/icassp49660.2025.10889617"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889617","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":"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":"https://openalex.org/A5073170842","display_name":"Ajat Shatru Arora","orcid":"https://orcid.org/0000-0003-4204-0150"},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Aadya Arora","raw_affiliation_strings":["Indian Institute Of Technology,Department of Electrical Engineering,Gandhinagar,Gujarat,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute Of Technology,Department of Electrical Engineering,Gandhinagar,Gujarat,India","institution_ids":["https://openalex.org/I27674431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007109424","display_name":"Vinay P. Namboodiri","orcid":"https://orcid.org/0000-0001-5262-9722"},"institutions":[{"id":"https://openalex.org/I51601045","display_name":"University of Bath","ror":"https://ror.org/002h8g185","country_code":"GB","type":"education","lineage":["https://openalex.org/I51601045"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vinay Namboodiri","raw_affiliation_strings":["University Of Bath,Department Of Computer Science,Bath,United Kingdom"],"affiliations":[{"raw_affiliation_string":"University Of Bath,Department Of Computer Science,Bath,United Kingdom","institution_ids":["https://openalex.org/I51601045"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5073170842"],"corresponding_institution_ids":["https://openalex.org/I27674431"],"apc_list":null,"apc_paid":null,"fwci":3.3919,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89913234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.9957000017166138,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.8103128671646118},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7569788098335266},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.7117437124252319},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6087610125541687},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.5470805764198303},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42381781339645386},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.42056405544281006},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3845304250717163},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3267974257469177},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.24228176474571228},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06046423316001892}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.8103128671646118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7569788098335266},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.7117437124252319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6087610125541687},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.5470805764198303},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42381781339645386},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.42056405544281006},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3845304250717163},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3267974257469177},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24228176474571228},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06046423316001892},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889617","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2928165649","https://openalex.org/W3094502228","https://openalex.org/W3138516171","https://openalex.org/W3166396011","https://openalex.org/W3168867926","https://openalex.org/W3198377975","https://openalex.org/W4312310776","https://openalex.org/W4312420092","https://openalex.org/W4364387763","https://openalex.org/W4366457071","https://openalex.org/W4366548765","https://openalex.org/W4385573131","https://openalex.org/W4387225969","https://openalex.org/W4389430914","https://openalex.org/W4390971106","https://openalex.org/W4391109864","https://openalex.org/W4391929768","https://openalex.org/W4401307635","https://openalex.org/W4402916510","https://openalex.org/W4407005368","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6851612810","https://openalex.org/W6851629250","https://openalex.org/W6852249959","https://openalex.org/W6870839691"],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W4294892107","https://openalex.org/W2357748469","https://openalex.org/W2392917037"],"abstract_inverted_index":{"With":[0],"the":[1,12,106,114,124,128,178,210,214],"popularity":[2],"of":[3,89,172],"foundational":[4,48],"models,":[5,31],"parameter":[6],"efficient":[7],"fine":[8],"tuning":[9],"has":[10],"become":[11],"defacto":[13],"approach":[14,180,202],"to":[15,19,42,84,101,120,130,205],"leverage":[16,85],"pretrained":[17,46,194],"models":[18],"perform":[20],"downstream":[21],"tasks.":[22],"Taking":[23],"inspiration":[24],"from":[25,139,177,192],"recent":[26],"advances":[27],"in":[28,79,105,116,123,147],"large":[29,71],"language":[30],"Visual":[32],"Prompt":[33],"Tuning,":[34],"and":[35,74,165,168,221],"similar":[36,141],"techniques,":[37],"learn":[38],"an":[39,144,170],"additional":[40],"prompt":[41],"efficiently":[43],"finetune":[44],"a":[45,97,148,193],"vision":[47],"model.":[49],"However,":[50],"we":[51,82],"observe":[52],"that":[53],"such":[54,63],"prompting":[55,99],"is":[56,70],"insufficient":[57],"for":[58,209],"fine-grained":[59],"visual":[60,98,103,118],"classification":[61,151,211],"tasks":[62],"as":[64,96],"medical":[65,159],"image":[66],"classification,":[67],"where":[68],"there":[69],"inter-class":[72],"variance,":[73],"small":[75],"intra-class":[76],"variance.":[77],"Hence,":[78],"this":[80],"paper":[81],"propose":[83],"advanced":[86],"segmentation":[87],"capabilities":[88],"Segment":[90],"Anything":[91],"Model":[92],"2":[93],"[1]":[94],"(SAM2)":[95],"cue":[100],"help":[102],"encoder":[104,119],"CLIP":[107,117,195],"[2]":[108],"(Contrastive":[109],"Language-Image":[110],"Pretraining)":[111],"by":[112],"guiding":[113],"attention":[115],"relevant":[121],"regions":[122],"image.":[125],"This":[126],"helps":[127],"model":[129,196],"focus":[131],"on":[132,157,181],"highly":[133],"discriminative":[134],"regions,":[135],"without":[136],"getting":[137],"distracted":[138],"visually":[140],"background":[142],"features,":[143],"essential":[145],"requirement":[146],"fewshot,":[149],"finegrained":[150],"setting.":[152],"We":[153],"evaluate":[154],"our":[155],"method":[156],"diverse":[158],"datasets":[160,186],"including":[161],"X-rays,":[162],"CT":[163],"scans,":[164],"MRI":[166],"images,":[167],"report":[169],"accuracy":[171],"(71%,":[173],"81%,":[174],"86%,":[175],"58%)":[176],"proposed":[179,201],"(COVID,":[182],"lung-disease,":[183],"brain-tumor,":[184],"breast-cancer)":[185],"against":[187],"(66%,":[188],"70%,":[189],"68%,":[190],"29%)":[191],"after":[197],"fewshot":[198],"training.":[199],"The":[200],"also":[203],"allows":[204],"obtain":[206],"interpretable":[207],"explanation":[208],"performance":[212],"through":[213],"localization":[215],"obtained":[216],"using":[217],"segmentation.":[218],"For":[219],"demonstrations":[220],"visualizations,":[222],"please":[223],"visit":[224],"https://aadya-arora.github.io/MedFocusClip/":[225]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}