{"id":"https://openalex.org/W7165680545","doi":"https://doi.org/10.48550/arxiv.2606.22660","title":"Prompting Diffusion Models for Zero-Shot Instance Segmentation","display_name":"Prompting Diffusion Models for Zero-Shot Instance Segmentation","publication_year":2026,"publication_date":"2026-06-21","ids":{"openalex":"https://openalex.org/W7165680545","doi":"https://doi.org/10.48550/arxiv.2606.22660"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.22660","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22660","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.2606.22660","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139197337","display_name":"Irem Zeynep Alag\u00f6z","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alag\u00f6z, Irem Zeynep","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092671769","display_name":"Nils Morbitzer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Morbitzer, Nils","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081937579","display_name":"Andrea Ramazzina","orcid":"https://orcid.org/0009-0001-0616-6875"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramazzina, Andrea","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139133167","display_name":"Nassir Navab","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Navab, Nassir","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139165394","display_name":"Federico Tombari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tombari, Federico","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000701918","display_name":"Stefano Gasperini","orcid":"https://orcid.org/0000-0002-7841-1569"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gasperini, Stefano","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.37059998512268066,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.37059998512268066,"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":0.12939999997615814,"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/T11094","display_name":"Face Recognition and Perception","score":0.09780000150203705,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"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/segmentation","display_name":"Segmentation","score":0.7135000228881836},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6990000009536743},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6244000196456909},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.578000009059906},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5580999851226807},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.5414000153541565},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4578999876976013},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42809998989105225},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38019999861717224}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7208999991416931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7206000089645386},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7135000228881836},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6990000009536743},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6244000196456909},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.578000009059906},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5580999851226807},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.5414000153541565},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4578999876976013},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42809998989105225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4025000035762787},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3714999854564667},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.35409998893737793},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.3215999901294708},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3165000081062317},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.3046000003814697},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.22660","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22660","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.2606.22660","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22660","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Several":[0],"disruptive":[1],"research":[2],"directions":[3],"have":[4,33],"recently":[5],"emerged":[6],"in":[7,18,41,218],"computer":[8],"vision,":[9],"including":[10,188],"foundation":[11,54],"models":[12,25,55],"achieving":[13],"previously":[14],"unseen":[15,169],"zero-shot":[16,163],"performance":[17],"scene":[19,42],"understanding,":[20],"even":[21],"interactively,":[22],"and":[23,67,157,172,192],"generative":[24,74,219],"that":[26,72,198,213],"synthesize":[27],"extremely":[28],"realistic":[29],"images.":[30],"The":[31],"latter":[32],"also":[34],"been":[35],"shown":[36],"to":[37,46,64,89,139,142,164,184],"be":[38],"highly":[39],"effective":[40],"understanding":[43],"tasks":[44],"thanks":[45],"their":[47],"rich":[48,215],"priors.":[49],"However,":[50],"for":[51,106],"promptable":[52],"segmentation,":[53],"struggle":[56],"with":[57,100,116,222],"accurately":[58],"segmenting":[59],"an":[60],"object's":[61],"region,":[62],"leading":[63],"false":[65],"positives":[66],"over-segmentation.":[68],"Notably,":[69],"early":[70],"attempts":[71],"leverage":[73],"priors":[75,216],"use":[76],"prompts":[77],"only":[78],"during":[79],"post-processing,":[80],"yielding":[81],"suboptimal":[82],"segments":[83],"because":[84],"the":[85,90,137,202,214],"process":[86],"is":[87],"agnostic":[88],"user":[91,143],"input.":[92],"In":[93],"this":[94],"paper,":[95],"we":[96,196],"target":[97],"these":[98],"limitations":[99],"Prompt2Seg,":[101],"a":[102,111,117,147,165,227],"spatial":[103,123,224],"conditioning":[104,118],"framework":[105],"diffusion-based":[107],"segmentation.":[108],"Prompt2Seg":[109,161,199],"augments":[110],"frozen":[112],"diffusion":[113,204],"segmentation":[114,205,234],"model":[115,138],"branch.":[119],"Our":[120,210],"approach":[121],"takes":[122],"prompts,":[124],"represented":[125],"as":[126,132],"2D":[127],"Gaussians":[128],"or":[129],"confidence":[130],"maps,":[131],"explicit":[133],"input":[134],"signals,":[135],"training":[136],"respond":[140],"directly":[141],"intent.":[144],"Fine-tuned":[145],"on":[146,177],"deliberately":[148],"constrained":[149],"set":[150],"of":[151,168],"object":[152,170],"categories":[153],"drawn":[154],"from":[155,181],"Hypersim":[156],"Virtual":[158],"KITTI":[159],"2,":[160],"generalizes":[162],"wide":[166],"range":[167],"types":[171],"visual":[173],"domains.":[174],"We":[175],"evaluate":[176],"seven":[178],"datasets":[179],"ranging":[180],"standard":[182],"benchmarks":[183],"more":[185],"challenging":[186],"domains,":[187],"paintings,":[189],"egocentric":[190],"views,":[191],"X-ray":[193],"data.":[194],"Furthermore,":[195],"demonstrate":[197],"consistently":[200],"outperforms":[201],"underlying":[203],"backbone":[206],"across":[207],"all":[208],"benchmarks.":[209],"results":[211],"suggest":[212],"encoded":[217],"pretraining,":[220],"combined":[221],"principled":[223],"conditioning,":[225],"offer":[226],"compelling":[228],"path":[229],"toward":[230],"broadly":[231],"generalizing":[232],"interactive":[233],"without":[235],"large-scale":[236],"mask":[237],"supervision.":[238]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-24T00:00:00"}