{"id":"https://openalex.org/W7172004444","doi":"https://doi.org/10.1145/3774521.3774606","title":"Self-Supervised Learning for Annotation-Efficient Endoscopic Instrument Segmentation","display_name":"Self-Supervised Learning for Annotation-Efficient Endoscopic Instrument Segmentation","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7172004444","doi":"https://doi.org/10.1145/3774521.3774606"},"language":null,"primary_location":{"id":"doi:10.1145/3774521.3774606","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774606","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/10.1145/3774521.3774606","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119212150","display_name":"Harinandan Shukla","orcid":null},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Harinandan Shukla","raw_affiliation_strings":["IITR, Roorkee, India"],"raw_orcid":"https://orcid.org/0009-0009-9991-3195","affiliations":[{"raw_affiliation_string":"IITR, Roorkee, India","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144170638","display_name":"Prankur Shukla","orcid":"https://orcid.org/0009-0005-1051-4923"},"institutions":[{"id":"https://openalex.org/I39244652","display_name":"Indian Institute of Information Technology, Design and Manufacturing, Kancheepuram","ror":"https://ror.org/023c9pb11","country_code":"IN","type":"education","lineage":["https://openalex.org/I39244652"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prankur Shukla","raw_affiliation_strings":["IIITDM Kancheepuram, Kancheepuram, India"],"raw_orcid":"https://orcid.org/0009-0005-1051-4923","affiliations":[{"raw_affiliation_string":"IIITDM Kancheepuram, Kancheepuram, India","institution_ids":["https://openalex.org/I39244652"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058647078","display_name":"Umarani Jayaraman","orcid":"https://orcid.org/0000-0002-9676-6291"},"institutions":[{"id":"https://openalex.org/I39244652","display_name":"Indian Institute of Information Technology, Design and Manufacturing, Kancheepuram","ror":"https://ror.org/023c9pb11","country_code":"IN","type":"education","lineage":["https://openalex.org/I39244652"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Umarani Jayaraman","raw_affiliation_strings":["IIITDM Kancheepuram, kancheepuram, India"],"raw_orcid":"https://orcid.org/0000-0002-9676-6291","affiliations":[{"raw_affiliation_string":"IIITDM Kancheepuram, kancheepuram, India","institution_ids":["https://openalex.org/I39244652"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7851999998092651},{"id":"https://openalex.org/keywords/dice","display_name":"Dice","score":0.5224999785423279},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5149999856948853},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5080999732017517},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.483599990606308},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45399999618530273},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.40939998626708984},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.38670000433921814}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8080999851226807},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7851999998092651},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.753600001335144},{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.5224999785423279},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5149999856948853},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5080999732017517},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.483599990606308},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45399999618530273},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.40939998626708984},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C163892561","wikidata":"https://www.wikidata.org/wiki/Q2613728","display_name":"S\u00f8rensen\u2013Dice coefficient","level":4,"score":0.3862999975681305},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3788999915122986},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.37310001254081726},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35580000281333923},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.34459999203681946},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30309998989105225},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.2759999930858612},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774521.3774606","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774606","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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:10.1145/3774521.3774606","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774606","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":10,"referenced_works":["https://openalex.org/W2133059825","https://openalex.org/W2137609262","https://openalex.org/W2145023731","https://openalex.org/W2412782625","https://openalex.org/W2798297683","https://openalex.org/W2912664121","https://openalex.org/W3035524453","https://openalex.org/W3211039391","https://openalex.org/W4389482752","https://openalex.org/W4392639484"],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"segmentation":[1,20,89,149],"of":[2,55,63,85,91,123,140,168,172,192,196,221,233],"surgical":[3],"instruments":[4],"in":[5,42,87],"endoscopic":[6,79],"procedures":[7],"is":[8,103,130,145],"critical":[9],"for":[10,181,241],"computer-assisted":[11],"interventions":[12],"and":[13,38,66,98,156,170,178,194,204,238],"robotic":[14],"surgery":[15],"systems.":[16],"Deep":[17],"learning-based":[18],"semantic":[19],"models":[21,136,164,188,215,224],"have":[22],"shown":[23],"state-of-the-art":[24],"performance":[25,90,129,220],"but":[26],"are":[27,36,110],"heavily":[28],"dependent":[29],"on":[30,115,138],"large-scale,":[31],"manually":[32],"annotated":[33],"datasets,":[34],"which":[35],"costly":[37],"time-consuming":[39],"to":[40,72,175],"obtain":[41],"the":[43,53,83,106,116,124,141,182,219,231],"medical":[44,242],"domain.":[45],"To":[46],"address":[47],"this":[48,50],"limitation,":[49],"study":[51],"explores":[52],"use":[54],"Self-Supervised":[56],"Learning":[57,62],"(SSL)":[58],"methods\u2014namely,":[59],"Simple":[60],"Contrastive":[61],"Representations":[64],"(SimCLR)":[65],"Momentum":[67],"Contrast":[68],"(MoCo)\u2014as":[69],"pretraining":[70],"strategies":[71],"enhance":[73],"feature":[74],"representation":[75],"learning":[76],"from":[77],"unlabeled":[78,117],"data.":[80,143],"We":[81],"evaluate":[82],"effectiveness":[84],"SSL":[86,114,199,234],"improving":[88],"two":[92],"widely":[93],"used":[94],"encoder-decoder":[95],"architectures:":[96],"U-Net":[97,163],"DeepLabV3+.":[99],"The":[100],"Kvasir-Instrument":[101],"dataset":[102],"employed":[104],"as":[105,235],"experimental":[107],"benchmark.":[108],"Models":[109],"first":[111],"pretrained":[112],"using":[113,147],"dataset,":[118],"then":[119],"fine-tuned":[120],"with":[121,198],"50%":[122],"available":[125],"labeled":[126,142],"samples.":[127],"Their":[128],"quantitatively":[131],"compared":[132,174],"against":[133],"fully":[134,183,208,222],"supervised":[135,184,223],"trained":[137],"100%":[139],"Evaluation":[144],"conducted":[146],"standard":[148],"metrics,":[150],"including":[151],"Dice":[152],"Similarity":[153],"Coefficient":[154],"(DSC)":[155],"Intersection-over-Union":[157],"(IoU).":[158],"Results":[159],"indicate":[160],"that":[161,213],"SSL-pretrained":[162,214],"achieve":[165,189],"a":[166,190,236],"DSC":[167,177,191,203],"0.832":[169],"IoU":[171,180,195,206],"0.735,":[173],"0.857":[176],"0.762":[179],"counterpart.":[185],"Similarly,":[186],"DeepLabV3+":[187],"0.844":[193],"0.748":[197],"pretraining,":[200],"versus":[201],"0.867":[202],"0.779":[205],"when":[207],"supervised.":[209],"These":[210],"findings":[211],"demonstrate":[212],"can":[216],"closely":[217],"match":[218],"while":[225],"requiring":[226],"significantly":[227],"fewer":[228],"annotations,":[229],"underscoring":[230],"potential":[232],"scalable":[237],"annotation-efficient":[239],"paradigm":[240],"image":[243],"segmentation.":[244]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}