{"id":"https://openalex.org/W7162455939","doi":"https://doi.org/10.48550/arxiv.2605.24533","title":"Learnable Shape Prototypes with Occlusion-Geometry-Guided Injection for Amodal Instance Segmentation","display_name":"Learnable Shape Prototypes with Occlusion-Geometry-Guided Injection for Amodal Instance Segmentation","publication_year":2026,"publication_date":"2026-05-23","ids":{"openalex":"https://openalex.org/W7162455939","doi":"https://doi.org/10.48550/arxiv.2605.24533"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.24533","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24533","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.2605.24533","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080617942","display_name":"\u5f20\u798f\u8303","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Fufan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130398028","display_name":"Jingxiang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jingxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137078423","display_name":"Xiangjie Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Xiangjie","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/T10036","display_name":"Advanced Neural Network Applications","score":0.1914999932050705,"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":0.1914999932050705,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.15870000422000885,"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":0.11230000108480453,"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/amodal-perception","display_name":"Amodal perception","score":0.7853000164031982},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7010999917984009},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.670799970626831},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4918000102043152},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4788999855518341},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.476500004529953},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.38989999890327454},{"id":"https://openalex.org/keywords/active-shape-model","display_name":"Active shape model","score":0.38830000162124634}],"concepts":[{"id":"https://openalex.org/C174478892","wikidata":"https://www.wikidata.org/wiki/Q4747455","display_name":"Amodal perception","level":3,"score":0.7853000164031982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7264000177383423},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7010999917984009},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.670799970626831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5965999960899353},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5902000069618225},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4918000102043152},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4788999855518341},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.476500004529953},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C129641003","wikidata":"https://www.wikidata.org/wiki/Q267189","display_name":"Active shape model","level":3,"score":0.38830000162124634},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3492000102996826},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3149999976158142},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.30469998717308044},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2653999924659729},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.24533","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24533","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.2605.24533","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24533","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":{"Amodal":[0],"instance":[1,141],"segmentation":[2,142],"aims":[3],"to":[4,50,84,111,119],"predict":[5],"the":[6,22,51,103,108,146,157,171,175,183,192,205,208],"complete":[7],"object":[8],"mask":[9,110],"including":[10],"occluded":[11,58,134,161],"regions":[12,128,162],"that":[13,78,145,191],"lack":[14],"pixel-level":[15],"observations":[16],"and":[17,40,57],"must":[18],"be":[19],"inferred":[20],"with":[21],"aid":[23],"of":[24,107,170,182,207],"shape":[25,30,68,74,87,131],"priors.":[26],"Existing":[27],"methods":[28],"acquire":[29],"priors":[31,88],"through":[32,89],"fixed-capacity":[33],"encoding":[34],"spaces":[35],"or":[36],"expensive":[37],"generative":[38],"models,":[39],"inject":[41],"them":[42],"uniformly":[43],"across":[44],"all":[45],"spatial":[46,97],"positions":[47],"without":[48],"adapting":[49],"varying":[52],"prior":[53,69,75],"demand":[54],"between":[55],"visible":[56,109,127],"regions.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"propose":[64],"a":[65,73],"gated":[66],"reliability-adaptive":[67],"framework,":[70],"which":[71],"introduces":[72],"memory":[76],"module":[77,195,210],"combines":[79],"learnable":[80],"prototypes":[81],"via":[82],"cross-attention":[83,194],"produce":[85],"instance-adaptive":[86],"weighted":[90],"prototype":[91],"combination":[92],"rather":[93],"than":[94],"generation.":[95],"A":[96],"adaptive":[98],"reliability":[99],"gate":[100],"then":[101],"employs":[102],"signed":[104],"distance":[105],"field":[106],"modulate":[112],"injection":[113],"intensity":[114],"at":[115],"each":[116],"position":[117],"according":[118],"its":[120],"occlusion":[121,198],"depth,":[122],"preserving":[123],"reliable":[124],"features":[125],"in":[126],"while":[129,178],"directing":[130],"compensation":[132],"toward":[133],"areas.":[135],"Experiments":[136],"on":[137,168],"two":[138,172],"mainstream":[139],"amodal":[140],"benchmarks":[143,173],"demonstrate":[144],"proposed":[147,209],"method":[148],"outperforms":[149],"existing":[150],"approaches":[151],"under":[152,174],"multiple":[153],"evaluation":[154],"settings,":[155],"improving":[156],"mean":[158],"intersection-over-union":[159],"over":[160,164],"by":[163],"11":[165],"percentage":[166],"points":[167],"one":[169],"standard":[176],"setting,":[177],"using":[179],"approximately":[180],"one-third":[181],"total":[184],"parameters.":[185],"Linear":[186],"probing":[187],"analysis":[188],"further":[189],"reveals":[190],"visible-mask":[193],"implicitly":[196],"encodes":[197],"geometry":[199],"into":[200],"visual":[201],"token":[202],"representations,":[203],"explaining":[204],"effectiveness":[206],"decomposition.":[211]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-27T00:00:00"}