{"id":"https://openalex.org/W4402916058","doi":"https://doi.org/10.1109/icip51287.2024.10647744","title":"Segment Any Object Model (SAOM): Real-To-Simulation Fine-Tuning Strategy For Multi-Class Multi-Instance Segmentation","display_name":"Segment Any Object Model (SAOM): Real-To-Simulation Fine-Tuning Strategy For Multi-Class Multi-Instance Segmentation","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402916058","doi":"https://doi.org/10.1109/icip51287.2024.10647744"},"language":"en","primary_location":{"id":"doi:10.1109/icip51287.2024.10647744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10647744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5056123575","display_name":"Mariia Khan","orcid":"https://orcid.org/0000-0001-6662-4607"},"institutions":[{"id":"https://openalex.org/I12079687","display_name":"Edith Cowan University","ror":"https://ror.org/05jhnwe22","country_code":"AU","type":"education","lineage":["https://openalex.org/I12079687"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mariia Khan","raw_affiliation_strings":["Edith Cowan University (ECU),School of Science,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Edith Cowan University (ECU),School of Science,Australia","institution_ids":["https://openalex.org/I12079687"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101846377","display_name":"Yue Qiu","orcid":"https://orcid.org/0000-0003-3869-2850"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Qiu","raw_affiliation_strings":["AIST,Artificial Intelligence Research Center (AIRC),Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIST,Artificial Intelligence Research Center (AIRC),Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100622051","display_name":"Yuren Cong","orcid":"https://orcid.org/0000-0001-7505-8563"},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yuren Cong","raw_affiliation_strings":["Institute for Information Processing, Leibniz University of Hannover (LUH),Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Information Processing, Leibniz University of Hannover (LUH),Germany","institution_ids":["https://openalex.org/I114112103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040412734","display_name":"Bodo Rosenhahn","orcid":"https://orcid.org/0000-0003-3861-1424"},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bodo Rosenhahn","raw_affiliation_strings":["Institute for Information Processing, Leibniz University of Hannover (LUH),Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Information Processing, Leibniz University of Hannover (LUH),Germany","institution_ids":["https://openalex.org/I114112103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072706685","display_name":"Jumana Abu-Khalaf","orcid":"https://orcid.org/0000-0002-6651-2880"},"institutions":[{"id":"https://openalex.org/I12079687","display_name":"Edith Cowan University","ror":"https://ror.org/05jhnwe22","country_code":"AU","type":"education","lineage":["https://openalex.org/I12079687"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jumana Abu-Khalaf","raw_affiliation_strings":["Edith Cowan University (ECU),School of Science,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Edith Cowan University (ECU),School of Science,Australia","institution_ids":["https://openalex.org/I12079687"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031492664","display_name":"David Suter","orcid":"https://orcid.org/0000-0001-6306-3023"},"institutions":[{"id":"https://openalex.org/I12079687","display_name":"Edith Cowan University","ror":"https://ror.org/05jhnwe22","country_code":"AU","type":"education","lineage":["https://openalex.org/I12079687"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Suter","raw_affiliation_strings":["Edith Cowan University (ECU),School of Science,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Edith Cowan University (ECU),School of Science,Australia","institution_ids":["https://openalex.org/I12079687"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"582","last_page":"588"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9430000185966492,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9430000185966492,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9332000017166138,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9330000281333923,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7473270297050476},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6527391672134399},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6373229026794434},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5858950018882751},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5591586232185364},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.47360992431640625},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45211681723594666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473270297050476},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6527391672134399},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6373229026794434},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5858950018882751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5591586232185364},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.47360992431640625},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45211681723594666}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip51287.2024.10647744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10647744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2604176797","https://openalex.org/W2963227409","https://openalex.org/W3008492644","https://openalex.org/W3009928773","https://openalex.org/W3173760279","https://openalex.org/W4386075709","https://openalex.org/W4390874575","https://openalex.org/W4391109864","https://openalex.org/W6747106673","https://openalex.org/W6747736218","https://openalex.org/W6757817989","https://openalex.org/W6760726409","https://openalex.org/W6778883912","https://openalex.org/W6780091408","https://openalex.org/W6799560697","https://openalex.org/W6850625674","https://openalex.org/W6851543690","https://openalex.org/W6851607685","https://openalex.org/W6852040150","https://openalex.org/W6852107595","https://openalex.org/W6852206773","https://openalex.org/W6852694211","https://openalex.org/W6852699137","https://openalex.org/W6852789751","https://openalex.org/W6852796095","https://openalex.org/W6852850613","https://openalex.org/W6853628691","https://openalex.org/W6853927381","https://openalex.org/W6854404163","https://openalex.org/W6855320001","https://openalex.org/W6855718977","https://openalex.org/W6860365250","https://openalex.org/W6860541660","https://openalex.org/W6867826459"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2737719445","https://openalex.org/W4239098401","https://openalex.org/W2501551404","https://openalex.org/W4385583601","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W2898210368","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Multi-class":[0],"multi-instance":[1,34],"segmentation":[2,35,54],"is":[3,29,125],"the":[4,17,45,106,111,176,183],"task":[5],"of":[6,16],"identifying":[7],"masks":[8,43,55],"for":[9,31,48,60,78,120,154],"multiple":[10,14],"object":[11,53,82,158],"classes":[12],"and":[13,84,147,182],"instances":[15],"same":[18],"class":[19],"within":[20],"an":[21],"image.":[22],"The":[23,180],"foundational":[24],"Segment":[25,98],"Anything":[26],"Model":[27,101],"(SAM)":[28],"designed":[30],"promptable":[32],"multi-class":[33],"but":[36],"tends":[37],"to":[38,103],"output":[39],"part":[40],"or":[41],"sub-part":[42],"in":[44,65,105,145,152,169],"\u201ceverything\u201d":[46,107],"mode":[47],"various":[49],"real-world":[50,177],"applications.":[51,67],"Whole":[52],"play":[56],"a":[57,70,141,148],"crucial":[58],"role":[59],"indoor":[61,157],"scene":[62],"understanding,":[63],"especially":[64],"robotics":[66],"We":[68,80],"propose":[69,110],"new":[71],"domain":[72],"invariant":[73],"Real-to-Simulation":[74,162],"(Real-Sim)":[75],"fine-tuning":[76,93,163],"strategy":[77,164],"SAM.":[79],"use":[81],"images":[83],"ground":[85],"truth":[86],"data":[87,178],"collected":[88,131],"from":[89,132],"Ai2Thor":[90,133],"simulator":[91],"during":[92],"(real-to-sim).":[94],"To":[95],"allow":[96],"our":[97,128,161],"Any":[99],"Object":[100],"(SAOM)":[102],"work":[104],"mode,":[108],"we":[109],"novel":[112],"nearest":[113],"neighbour":[114],"assignment":[115],"method,":[116],"updating":[117],"point":[118],"embeddings":[119],"each":[121],"ground-truth":[122],"mask.":[123],"SAOM":[124,135],"evaluated":[126],"on":[127,138,175],"own":[129],"dataset":[130,181],"simulator.":[134],"significantly":[136],"improves":[137],"SAM,":[139],"with":[140],"$28":[142],"\\%$":[143,150],"increase":[144,151],"mIoU":[146],"$25":[149],"mAcc":[153],"54":[155],"frequently-seen":[156],"classes.":[159],"Moreover,":[160],"demonstrates":[165],"promising":[166],"generalization":[167],"performance":[168],"real":[170],"environments":[171],"without":[172],"being":[173],"trained":[174],"(sim-to-real).":[179],"code":[184],"are":[185],"available":[186],"here.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}