{"id":"https://openalex.org/W7172001896","doi":"https://doi.org/10.1145/3774521.3774567","title":"CP-SIS: Learnable Class Prototypes for Efficient Surgical Instrument Segmentation","display_name":"CP-SIS: Learnable Class Prototypes for Efficient Surgical Instrument Segmentation","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7172001896","doi":"https://doi.org/10.1145/3774521.3774567"},"language":null,"primary_location":{"id":"doi:10.1145/3774521.3774567","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774567","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774521.3774567","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036268638","display_name":"Kunal Dargan","orcid":null},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kunal Dargan","raw_affiliation_strings":["School of Information Technology, Indian Institute of Technology Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0009-0006-5947-1933","affiliations":[{"raw_affiliation_string":"School of Information Technology, Indian Institute of Technology Delhi, Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102836879","display_name":"Nikhil Reddy","orcid":"https://orcid.org/0000-0003-1127-1271"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nikhil Kumar Jangamreddy","raw_affiliation_strings":["UQ-IITD Research Academy, Indian Institute of Technology Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0000-0003-1127-1271","affiliations":[{"raw_affiliation_string":"UQ-IITD Research Academy, Indian Institute of Technology Delhi, Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101532736","display_name":"Chetan Arora","orcid":"https://orcid.org/0000-0003-0155-0250"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chetan Arora","raw_affiliation_strings":["Computer Science and Engineering, Indian Institute of Technology Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0000-0003-0155-0250","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology Delhi, Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I68891433"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7621999979019165},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6978999972343445},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6626999974250793},{"id":"https://openalex.org/keywords/unavailability","display_name":"Unavailability","score":0.6351000070571899},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5365999937057495},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4684999883174896},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44760000705718994},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.41290000081062317}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7621999979019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7235999703407288},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6978999972343445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6822999715805054},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6626999974250793},{"id":"https://openalex.org/C2780505938","wikidata":"https://www.wikidata.org/wiki/Q17093282","display_name":"Unavailability","level":2,"score":0.6351000070571899},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5365999937057495},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4684999883174896},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44760000705718994},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.41290000081062317},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3725000023841858},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36730000376701355},{"id":"https://openalex.org/C2778181360","wikidata":"https://www.wikidata.org/wiki/Q1074814","display_name":"Surgical instrument","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.34299999475479126},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3244999945163727},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.3100999891757965},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.2603999972343445}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774521.3774567","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774567","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774521.3774567","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774567","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2519007024","https://openalex.org/W2601943843","https://openalex.org/W2980225217","https://openalex.org/W2993690044","https://openalex.org/W3095500987","https://openalex.org/W3096104140","https://openalex.org/W3152803807","https://openalex.org/W4205991051","https://openalex.org/W4221148496","https://openalex.org/W4221166280","https://openalex.org/W4296193539","https://openalex.org/W4308235509","https://openalex.org/W4312517597","https://openalex.org/W4312749849","https://openalex.org/W4313156423","https://openalex.org/W4319301126","https://openalex.org/W4386071535","https://openalex.org/W4386362522","https://openalex.org/W4387225945","https://openalex.org/W4390874575","https://openalex.org/W4391109864","https://openalex.org/W4393159543","https://openalex.org/W4397015231","https://openalex.org/W4403062944","https://openalex.org/W4403063149","https://openalex.org/W4403069407","https://openalex.org/W4406138162","https://openalex.org/W4406238026","https://openalex.org/W4412568772","https://openalex.org/W7133204184","https://openalex.org/W7133233472"],"related_works":[],"abstract_inverted_index":{"Surgical":[0],"Instrument":[1],"Segmentation":[2],"(SIS)":[3],"is":[4],"vital":[5],"for":[6,28,71,81,107,128],"visual":[7,55],"understanding":[8],"in":[9,50,182],"Robot-Assisted":[10],"Surgery":[11],"(RAS).":[12],"Recently,":[13],"Vision":[14],"Foundation":[15],"Models":[16],"(VFMs)":[17],"have":[18],"shown":[19],"strong":[20],"generalization":[21],"capabilities":[22],"on":[23,147,166,184,195],"unseen":[24],"target":[25],"domains.":[26],"However,":[27],"the":[29,72,82,112,126,156,172,196],"SIS":[30,54,76],"task":[31],"both":[32],"zero":[33],"shot":[34],"use":[35],"of":[36,67,135,145],"VFMs":[37],"or":[38],"fine-tuning":[39,130],"them":[40],"fail":[41],"to":[42,53,177],"generalize":[43],"effectively.":[44],"Arrising":[45],"from:":[46],"(1)":[47],"domain":[48],"gap":[49],"natural":[51],"imags":[52],"context,":[56],"(2)":[57],"severe":[58],"class":[59,142],"imbalance":[60],"coupled":[61],"with":[62,94,103],"fine-grained":[63],"classes,":[64,86],"(3)":[65],"unavailability":[66],"good":[68],"descriptive":[69],"prompts":[70],"surgical":[73],"instruments.":[74],"Existing":[75],"methods":[77],"show":[78],"high":[79],"affinity":[80],"more":[83],"frequent":[84],"instrument":[85],"restricting":[87],"clinical":[88],"application.":[89],"We":[90,110,138],"address":[91],"these":[92],"challenges":[93],"CP-SIS,":[95],"a":[96,120,140,178],"novel":[97],"Learnable":[98],"Class":[99],"Prototype":[100],"Queries":[101],"framework":[102],"Low-Rank":[104],"Adaptation":[105],"(LoRA)":[106],"VFM":[108],"adaptation.":[109],"follow":[111],"mask-classification":[113],"paradigm,":[114],"our":[115],"method":[116,174],"takes":[117],"proposals":[118],"from":[119],"pretrained":[121],"instance":[122],"segmentation":[123],"model,":[124],"avoiding":[125],"need":[127],"full":[129],"and":[131,149,164],"adapting":[132],"only":[133],"3%":[134],"model":[136],"parameters.":[137],"report":[139],"mean":[141],"IoU":[143,183],"(mcIoU)":[144],"50.83%":[146],"challenging":[148],"real-world":[150],"Endovis":[151,167],"2018":[152],"validation":[153],"set,":[154],"surpassing":[155],"best":[157],"fully":[158],"fine-tuned":[159],"frame-level":[160],"baseline":[161],"by":[162],"4.5%":[163],"50.07%":[165],"2017":[168],"four-fold":[169],"average.":[170],"Notably,":[171],"proposed":[173],"shows":[175],"up":[176],"64%":[179],"relative":[180],"improvement":[181],"minority":[185],"classes":[186],"(with":[187],"\u2264":[188],"2%":[189],"prevalence),":[190],"while":[191],"maintaining":[192],"competitive":[193],"performance":[194],"majority":[197],"classes.":[198],"https://github.com/Kunaldargan/CP_SIS":[199]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}