{"id":"https://openalex.org/W6979259019","doi":null,"title":"Segment Anything, Even Occluded","display_name":"Segment Anything, Even Occluded","publication_year":2025,"publication_date":"2025-03-08","ids":{"openalex":"https://openalex.org/W6979259019"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2503.06261","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.06261","pdf_url":"https://arxiv.org/pdf/2503.06261","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.06261","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tai, Wei-En","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tai, Wei-En","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shih, Yu-Lin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shih, Yu-Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123961711","display_name":"Cheng Sun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Yu-Chiang Frank","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yu-Chiang Frank","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Chen, Hwann-Tzong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hwann-Tzong","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":true,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.98580002784729,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.98580002784729,"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":0.005499999970197678,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0031999999191612005,"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/segment-anything-model","display_name":"Segment Anything Model","score":0.9769999980926514},{"id":"https://openalex.org/keywords/mask-decoder","display_name":"mask decoder","score":0.8259999752044678},{"id":"https://openalex.org/keywords/synthetic-dataset","display_name":"synthetic dataset","score":0.7289999723434448},{"id":"https://openalex.org/keywords/zero-shot-generalization","display_name":"zero-shot generalization","score":0.7229999899864197}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7694000005722046},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7651000022888184},{"id":"https://openalex.org/C174478892","wikidata":"https://www.wikidata.org/wiki/Q4747455","display_name":"Amodal perception","level":3,"score":0.651199996471405},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6335999965667725},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6183000206947327},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6134999990463257},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5091999769210815},{"id":"https://openalex.org/C2776303644","wikidata":"https://www.wikidata.org/wiki/Q1020499","display_name":"Interfacing","level":2,"score":0.4943000078201294},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.44929999113082886},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.36970001459121704},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C121535716","wikidata":"https://www.wikidata.org/wiki/Q340600","display_name":"Achromatic lens","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2503.06261","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.06261","pdf_url":"https://arxiv.org/pdf/2503.06261","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.06261","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.06261","pdf_url":"https://arxiv.org/pdf/2503.06261","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Amodal":[0],"instance":[1],"segmentation,":[2],"which":[3],"aims":[4],"to":[5,51,88,166],"detect":[6],"and":[7,11,30,41,49,120,158],"segment":[8],"both":[9,38,156],"visible":[10],"invisible":[12],"parts":[13],"of":[14,55,82,100],"objects":[15],"in":[16,22],"images,":[17],"plays":[18],"a":[19,66,77,108],"crucial":[20],"role":[21],"various":[23,85],"applications":[24],"including":[25,149],"autonomous":[26],"driving,":[27],"robotic":[28],"manipulation,":[29],"scene":[31],"understanding.":[32],"While":[33],"existing":[34],"methods":[35],"require":[36],"training":[37,128],"front-end":[39,86],"detectors":[40,87],"mask":[42,79,90],"decoders":[43],"jointly,":[44],"this":[45,61],"approach":[46],"lacks":[47],"flexibility":[48],"fails":[50],"leverage":[52],"the":[53,71,98,117,127,145],"strengths":[54],"pre-existing":[56],"modal":[57,118],"detectors.":[58],"To":[59],"address":[60],"limitation,":[62],"we":[63,105],"propose":[64],"SAMEO,":[65],"novel":[67],"framework":[68],"that":[69,139],"adapts":[70],"Segment":[72],"Anything":[73],"Model":[74],"(SAM)":[75],"as":[76],"versatile":[78],"decoder":[80],"capable":[81],"interfacing":[83],"with":[84],"enable":[89],"prediction":[91],"even":[92],"for":[93,131,164],"partially":[94],"occluded":[95],"objects.":[96],"Acknowledging":[97],"constraints":[99],"limited":[101],"amodal":[102,132],"segmentation":[103,133],"datasets,":[104],"introduce":[106],"Amodal-LVIS,":[107,150],"large-scale":[109],"synthetic":[110],"dataset":[111,124],"comprising":[112],"300K":[113],"images":[114],"derived":[115],"from":[116],"LVIS":[119],"LVVIS":[121],"datasets.":[122],"This":[123],"significantly":[125],"expands":[126],"data":[129],"available":[130],"research.":[134],"Our":[135],"experimental":[136],"results":[137],"demonstrate":[138],"our":[140],"approach,":[141],"when":[142],"trained":[143],"on":[144,155],"newly":[146],"extended":[147],"dataset,":[148],"achieves":[151],"remarkable":[152],"zero-shot":[153],"performance":[154],"COCOA-cls":[157],"D2SA":[159],"benchmarks,":[160],"highlighting":[161],"its":[162],"potential":[163],"generalization":[165],"unseen":[167],"scenarios.":[168]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}