{"id":"https://openalex.org/W4386554697","doi":"https://doi.org/10.48550/arxiv.2309.03179","title":"SLiMe: Segment Like Me","display_name":"SLiMe: Segment Like Me","publication_year":2023,"publication_date":"2023-09-06","ids":{"openalex":"https://openalex.org/W4386554697","doi":"https://doi.org/10.48550/arxiv.2309.03179"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2309.03179","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.03179","pdf_url":"https://arxiv.org/pdf/2309.03179","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.03179","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062489332","display_name":"Aliasghar Khani","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1286353243","display_name":"Autodesk (United States)","ror":"https://ror.org/00pkt4594","country_code":"US","type":"company","lineage":["https://openalex.org/I1286353243"]},{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Khani, Aliasghar","raw_affiliation_strings":["Autodesk Research","School of Computing Science , Simon Fraser University SLiMe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autodesk Research","institution_ids":["https://openalex.org/I1286353243"]},{"raw_affiliation_string":"School of Computing Science , Simon Fraser University SLiMe","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007863579","display_name":"Saeid Asgari Taghanaki","orcid":"https://orcid.org/0000-0002-9183-0266","observed_orcids":["https://orcid.org/0000-0002-9183-0266"]},"institutions":[{"id":"https://openalex.org/I1286353243","display_name":"Autodesk (United States)","ror":"https://ror.org/00pkt4594","country_code":"US","type":"company","lineage":["https://openalex.org/I1286353243"]},{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Taghanaki, Saeid Asgari","raw_affiliation_strings":["Autodesk Research","School of Computing Science , Simon Fraser University SLiMe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autodesk Research","institution_ids":["https://openalex.org/I1286353243"]},{"raw_affiliation_string":"School of Computing Science , Simon Fraser University SLiMe","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020352776","display_name":"Aditya Sanghi","orcid":"https://orcid.org/0000-0003-1554-2278","observed_orcids":["https://orcid.org/0000-0003-1554-2278"]},"institutions":[{"id":"https://openalex.org/I1286353243","display_name":"Autodesk (United States)","ror":"https://ror.org/00pkt4594","country_code":"US","type":"company","lineage":["https://openalex.org/I1286353243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanghi, Aditya","raw_affiliation_strings":["Autodesk Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autodesk Research","institution_ids":["https://openalex.org/I1286353243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021862056","display_name":"Ali Mahdavi Amiri","orcid":"https://orcid.org/0000-0002-4693-3565","observed_orcids":["https://orcid.org/0000-0002-4693-3565"]},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Amiri, Ali Mahdavi","raw_affiliation_strings":["School of Computing Science , Simon Fraser University SLiMe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Science , Simon Fraser University SLiMe","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072684302","display_name":"Ghassan Hamarneh","orcid":"https://orcid.org/0000-0001-5040-7448","observed_orcids":["https://orcid.org/0000-0001-5040-7448"]},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hamarneh, Ghassan","raw_affiliation_strings":["School of Computing Science , Simon Fraser University SLiMe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Science , Simon Fraser University SLiMe","institution_ids":["https://openalex.org/I18014758"]}]}],"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":true,"cited_by_count":18,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.8788999915122986,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.8788999915122986,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.07119999825954437,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.027499999850988388,"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/few-shot-segmentation","display_name":"few-shot segmentation","score":0.9539999961853027},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8349999785423279},{"id":"https://openalex.org/keywords/stable-diffusion","display_name":"Stable Diffusion","score":0.9769999980926514},{"id":"https://openalex.org/keywords/attention-maps","display_name":"attention maps","score":0.8009999990463257},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"image segmentation","score":0.3490000069141388},{"id":"https://openalex.org/keywords/self-attention","display_name":"self-attention","score":0.34299999475479126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401800155639648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7205772399902344},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.7118104100227356},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.702157199382782},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5904632806777954},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5152440667152405},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5132076740264893},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5007944107055664},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4959309995174408},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48055675625801086},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.4798997640609741},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4324718117713928},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4298100471496582},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06727489829063416},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2309.03179","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.03179","pdf_url":"https://arxiv.org/pdf/2309.03179","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2309.03179","doi":"https://doi.org/10.48550/arxiv.2309.03179","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2309.03179","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.03179","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.03179","pdf_url":"https://arxiv.org/pdf/2309.03179","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386554697.pdf","grobid_xml":"https://content.openalex.org/works/W4386554697.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2630837129","https://openalex.org/W4200632170","https://openalex.org/W4289785045","https://openalex.org/W4289785095","https://openalex.org/W4309957798","https://openalex.org/W4365456721","https://openalex.org/W4390872477","https://openalex.org/W4390873795","https://openalex.org/W4402187257","https://openalex.org/W4402817070","https://openalex.org/W7133244048"],"related_works":["https://openalex.org/W4402727134","https://openalex.org/W4417281279","https://openalex.org/W7223240794","https://openalex.org/W4407123997","https://openalex.org/W7140316099","https://openalex.org/W4410738052","https://openalex.org/W4226452378","https://openalex.org/W4415055544","https://openalex.org/W4403570162","https://openalex.org/W7160326536"],"abstract_inverted_index":{"Significant":[0],"strides":[1],"have":[2],"been":[3],"made":[4],"using":[5,46,91,164],"large":[6],"vision-language":[7,37],"models,":[8],"like":[9],"Stable":[10,100],"Diffusion":[11,101],"(SD),":[12],"for":[13,39],"a":[14,66,111,185],"variety":[15],"of":[16,99,107,156,180,188],"downstream":[17],"tasks,":[18],"including":[19,79],"image":[20,22,69,150],"editing,":[21],"correspondence,":[23],"and":[24,70,194,202],"3D":[25],"shape":[26],"generation.":[27],"Inspired":[28],"by":[29,53],"these":[30,35],"advancements,":[31],"we":[32,74],"explore":[33],"leveraging":[34,169],"extensive":[36],"models":[38],"segmenting":[40],"images":[41],"at":[42],"any":[43,148],"desired":[44],"granularity":[45,155],"as":[47,49,60],"few":[48],"one":[50,166],"annotated":[51],"sample":[52],"proposing":[54],"SLiMe.":[55,181],"SLiMe":[56,145,197],"frames":[57],"this":[58],"problem":[59],"an":[61],"optimization":[62],"task.":[63],"Specifically,":[64],"given":[65],"single":[67,112],"training":[68,117,162,171],"its":[71],"segmentation":[72,141,204],"mask,":[73],"first":[75],"extract":[76],"attention":[77,94,129],"maps,":[78,95,130],"our":[80],"novel":[81],"\"weighted":[82],"accumulated":[83],"self-attention":[84],"map\"":[85],"from":[86,115],"the":[87,92,96,116,124,128,140,154,157,161,178],"SD":[88],"prior.":[89],"Then,":[90],"extracted":[93],"text":[97],"embeddings":[98,121],"are":[102],"optimized":[103],"such":[104],"that,":[105],"each":[106],"them,":[108],"learn":[109],"about":[110],"segmented":[113,125,158],"region":[114,126,159],"image.":[118],"These":[119],"learned":[120],"then":[122,135],"highlight":[123],"in":[127,132,160],"which":[131],"turn":[133],"can":[134],"be":[136],"used":[137],"to":[138,146],"derive":[139],"map.":[142],"This":[143],"enables":[144],"segment":[147],"real-world":[149],"during":[151],"inference":[152],"with":[153],"image,":[163],"just":[165],"example.":[167],"Moreover,":[168],"additional":[170],"data":[172],"when":[173],"available,":[174],"i.e.":[175],"few-shot,":[176],"improves":[177],"performance":[179],"We":[182],"carried":[183],"out":[184],"knowledge-rich":[186],"set":[187],"experiments":[189],"examining":[190],"various":[191],"design":[192],"factors":[193],"showed":[195],"that":[196],"outperforms":[198],"other":[199],"existing":[200],"one-shot":[201],"few-shot":[203],"methods.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-09-09T00:00:00"}