{"id":"https://openalex.org/W7166017693","doi":"https://doi.org/10.48550/arxiv.2606.26711","title":"Mask to Concept: Auto-Promptable SAM3 via Efficient Test-Time Concept Embedding Search for Few-Shot Annotation","display_name":"Mask to Concept: Auto-Promptable SAM3 via Efficient Test-Time Concept Embedding Search for Few-Shot Annotation","publication_year":2026,"publication_date":"2026-06-25","ids":{"openalex":"https://openalex.org/W7166017693","doi":"https://doi.org/10.48550/arxiv.2606.26711"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.26711","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26711","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.26711","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139416230","display_name":"Quan Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Quan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111153494","display_name":"Shaoqing Zhai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhai, Shaoqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139423923","display_name":"Qiang Hu Jia Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Qiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141599460","display_name":"Jia Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139401688","display_name":"Qiang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Qiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5141739230","display_name":"Zhiwei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6607000231742859,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6607000231742859,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.08070000261068344,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.07840000092983246,"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/annotation","display_name":"Annotation","score":0.7702999711036682},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7231000065803528},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6556000113487244},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5892000198364258},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.531499981880188},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5083000063896179},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.48899999260902405},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4377000033855438},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4065000116825104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8064000010490417},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7702999711036682},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7231000065803528},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6556000113487244},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5892000198364258},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.531499981880188},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5083000063896179},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.48899999260902405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4884999990463257},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4065000116825104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37459999322891235},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3467000126838684},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.28870001435279846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2824999988079071},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27900001406669617},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.26669999957084656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.26711","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26711","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.26711","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26711","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.598152756690979,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Transforming":[0],"foundation":[1],"segmentation":[2,45,141,209,218],"models":[3],"from":[4],"human-prompted":[5],"tools":[6],"into":[7],"auto-promptable":[8],"annotators":[9],"is":[10,56],"critical":[11],"for":[12,86,111,176,192],"scalable":[13,231],"medical":[14,54,87,208,232],"data":[15],"annotation.":[16],"Current":[17],"methods":[18],"commonly":[19],"depend":[20],"on":[21,207],"external":[22,91],"feature":[23],"matchers":[24],"or":[25,95],"auxiliary":[26],"networks":[27],"to":[28,77,108,128,162,187,189],"automate":[29],"geometric":[30],"prompting,":[31],"but":[32],"introducing":[33],"architectural":[34],"overhead":[35],"and":[36,65,131,157,179,220,227],"limiting":[37],"performance":[38,219],"scalability.":[39],"Although":[40],"SAM3":[41,85,107],"natively":[42],"supports":[43],"concept":[44,124,140,159,195],"via":[46],"reusable":[47],"text":[48,97],"prompts,":[49,165],"its":[50,117],"direct":[51],"use":[52],"in":[53],"imaging":[55],"hindered":[57],"by":[58,135],"a":[59,101,122,146,198,225],"lack":[60],"of":[61,68,137],"fine-grained":[62],"clinical":[63],"knowledge":[64],"the":[66,133,139,154,163,180],"ambiguity":[67],"human-written":[69],"descriptions.":[70],"In":[71],"this":[72],"work,":[73],"we":[74],"propose":[75],"Mask":[76],"Concept":[78],"(M2C),":[79],"an":[80],"efficient":[81,228],"framework":[82],"that":[83,152,212],"adapts":[84],"few-shot":[88,217],"annotation":[89,200,222],"without":[90],"modules,":[92],"parameter":[93],"retraining,":[94],"manual":[96],"engineering.":[98],"Using":[99],"only":[100],"few":[102],"labeled":[103],"images,":[104],"M2C":[105,188],"enables":[106],"automatically":[109],"search":[110,191],"transferable":[112],"visual":[113],"concepts":[114],"entirely":[115],"within":[116],"frozen":[118],"architecture:":[119],"it":[120,127],"initializes":[121],"learnable":[123],"embedding,":[125],"uses":[126],"prompt":[129],"segmentation,":[130],"updates":[132],"embedding":[134],"gradients":[136],"minimizing":[138],"error.":[142],"We":[143],"further":[144],"introduce":[145],"Hybrid":[147],"Uncertainty":[148],"Estimation":[149],"(HUE)":[150],"module":[151],"calculates":[153],"prediction":[155],"entropy":[156],"maps":[158],"predictions":[160],"back":[161,186],"box":[164],"measuring":[166],"concept-geometry":[167],"prompting":[168],"inconsistency.":[169],"Highly":[170],"uncertain":[171],"samples":[172],"are":[173,183,236],"flagged":[174],"actively":[175],"human":[177],"correction,":[178],"corrected":[181],"masks":[182],"then":[184],"fed":[185],"continuously":[190],"more":[193],"precise":[194],"embeddings,":[196],"forming":[197],"self-enhancing":[199],"loop":[201],"with":[202],"minimal":[203],"expert":[204],"effort.":[205],"Experiments":[206],"benchmarks":[210],"show":[211],"our":[213],"method":[214],"achieves":[215],"SOTA":[216],"outstanding":[221],"efficiency,":[223],"offering":[224],"practical":[226],"pathway":[229],"toward":[230],"image":[233],"labeling.":[234],"Codes":[235],"at":[237],"https://github.com/Huster-Hq/M2C.":[238]},"counts_by_year":[],"updated_date":"2026-07-23T13:24:44.402172","created_date":"2026-06-27T00:00:00"}