{"id":"https://openalex.org/W4387171244","doi":"https://doi.org/10.3233/faia230485","title":"Instance-Aware Diffusion Implicit Process for Box-Based Instance Segmentation","display_name":"Instance-Aware Diffusion Implicit Process for Box-Based Instance Segmentation","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387171244","doi":"https://doi.org/10.3233/faia230485"},"language":"en","primary_location":{"id":"doi:10.3233/faia230485","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230485","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230485","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230485","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107004316","display_name":"Hao Ren","orcid":"https://orcid.org/0000-0002-5639-450X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Ren","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046584727","display_name":"Xingsong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingsong Liu","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107004055","display_name":"Junjian Huang","orcid":"https://orcid.org/0009-0001-8526-5248"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjian Huang","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101721258","display_name":"Ru Wan","orcid":"https://orcid.org/0009-0008-8151-0059"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ru Wan","raw_affiliation_strings":["Mogo.ai Information and Technology Co., Ltd., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mogo.ai Information and Technology Co., Ltd., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058626590","display_name":"Jian Pu","orcid":"https://orcid.org/0000-0002-0892-1213"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210164150","display_name":"Shanghai Center for Brain Science and Brain-Inspired Technology","ror":"https://ror.org/0551a0y31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210164150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Pu","raw_affiliation_strings":["Institute of Science and Technology for Brain-inspired Intelligence, Fudan University","Institute of Science and Technology for Brain-inspired Intelligence, Fudan University c Mogo.ai Information and Technology Co., Ltd., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science and Technology for Brain-inspired Intelligence, Fudan University","institution_ids":["https://openalex.org/I4210164150","https://openalex.org/I24943067"]},{"raw_affiliation_string":"Institute of Science and Technology for Brain-inspired Intelligence, Fudan University c Mogo.ai Information and Technology Co., Ltd., Shanghai, China","institution_ids":["https://openalex.org/I4210164150","https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070355771","display_name":"Hong Lu","orcid":"https://orcid.org/0000-0002-4572-2854"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Lu","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36112766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9969000220298767,"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":0.9969000220298767,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9944000244140625,"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":0.9873999953269958,"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":0.7870556116104126},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6813726425170898},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.672625720500946},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6578304171562195},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6276711225509644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6179047226905823},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5383335947990417},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5121719837188721},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4730343520641327},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4572036862373352},{"id":"https://openalex.org/keywords/region-of-interest","display_name":"Region of interest","score":0.42082643508911133},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3752104640007019},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35063785314559937}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7870556116104126},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6813726425170898},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.672625720500946},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6578304171562195},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6276711225509644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6179047226905823},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5383335947990417},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5121719837188721},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4730343520641327},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4572036862373352},{"id":"https://openalex.org/C19609008","wikidata":"https://www.wikidata.org/wiki/Q2138203","display_name":"Region of interest","level":2,"score":0.42082643508911133},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3752104640007019},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35063785314559937},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230485","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230485","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230485","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia230485","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230485","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230485","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387171244.pdf","grobid_xml":"https://content.openalex.org/works/W4387171244.grobid-xml"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1915786104","https://openalex.org/W2108598243","https://openalex.org/W2129069237","https://openalex.org/W2194775991","https://openalex.org/W2432481613","https://openalex.org/W2565639579","https://openalex.org/W2749895778","https://openalex.org/W2772955562","https://openalex.org/W2793693263","https://openalex.org/W2884561390","https://openalex.org/W2908510526","https://openalex.org/W2923575270","https://openalex.org/W2928502868","https://openalex.org/W2941956444","https://openalex.org/W2949033552","https://openalex.org/W2950628590","https://openalex.org/W2959300817","https://openalex.org/W2959581809","https://openalex.org/W2962766617","https://openalex.org/W2962914239","https://openalex.org/W2963857746","https://openalex.org/W2964241181","https://openalex.org/W2976982891","https://openalex.org/W2981342784","https://openalex.org/W2982161360","https://openalex.org/W2982220924","https://openalex.org/W2987206775","https://openalex.org/W2993182889","https://openalex.org/W2997277830","https://openalex.org/W3030520226","https://openalex.org/W3034681942","https://openalex.org/W3034826836","https://openalex.org/W3035049382","https://openalex.org/W3035384201","https://openalex.org/W3036167779","https://openalex.org/W3092442149","https://openalex.org/W3093600664","https://openalex.org/W3096609285","https://openalex.org/W3105013723","https://openalex.org/W3110402800","https://openalex.org/W3113410735","https://openalex.org/W3117876421","https://openalex.org/W3121370741","https://openalex.org/W3122887982","https://openalex.org/W3138901262","https://openalex.org/W3148566359","https://openalex.org/W3162926177","https://openalex.org/W3167260844","https://openalex.org/W3167308647","https://openalex.org/W3168053944","https://openalex.org/W3168783492","https://openalex.org/W3172752666","https://openalex.org/W3177248696","https://openalex.org/W3184439416","https://openalex.org/W3217345456","https://openalex.org/W4221162716","https://openalex.org/W4225275515","https://openalex.org/W4226317937","https://openalex.org/W4239072543","https://openalex.org/W4309398566","https://openalex.org/W4310921259","https://openalex.org/W4312388283","https://openalex.org/W4312460151","https://openalex.org/W4312933868","https://openalex.org/W4323520574","https://openalex.org/W4327672567","https://openalex.org/W4360884927","https://openalex.org/W4386066020"],"related_works":["https://openalex.org/W2073139667","https://openalex.org/W2729514902","https://openalex.org/W2024160000","https://openalex.org/W2517104666","https://openalex.org/W2773500201","https://openalex.org/W2061273563","https://openalex.org/W2005437358","https://openalex.org/W1669643531","https://openalex.org/W4287995534","https://openalex.org/W2743258233"],"abstract_inverted_index":{"The":[0],"diffusion":[1,90],"model":[2],"has":[3],"demonstrated":[4],"impressive":[5],"performance":[6],"in":[7],"image":[8],"generation,":[9],"but":[10],"its":[11,126],"potential":[12],"for":[13,34,67],"discriminative":[14],"tasks":[15],"such":[16],"as":[17],"instance":[18,35],"segmentation":[19,36],"remains":[20],"unexplored.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25],"propose":[26],"an":[27],"Instance-aware":[28],"Diffusion":[29],"Implicit":[30],"Process":[31],"(IDIP)":[32],"framework":[33],"based":[37,102],"on":[38,103,112],"boxes.":[39,106],"During":[40,79],"training,":[41],"IDIP":[42,81],"diffuses":[43],"ground-truth":[44],"boxes":[45,64,86],"across":[46],"various":[47],"time":[48],"steps,":[49],"extracting":[50],"corresponding":[51],"Region":[52],"of":[53],"Interest":[54],"(RoI)":[55],"features.":[56],"Dynamic":[57],"convolution":[58],"is":[59],"then":[60],"used":[61],"to":[62,125],"predict":[63],"and":[65,70,120,129],"categories":[66],"each":[68],"RoI,":[69],"the":[71,88,94,104,113],"mask":[72,95],"head":[73,96],"generates":[74],"masks":[75,99],"from":[76,100],"these":[77],"predictions.":[78],"inference,":[80],"iteratively":[82],"refines":[83],"randomly":[84],"generated":[85],"with":[87],"denoising":[89],"implicit":[91],"model,":[92],"while":[93],"derives":[97],"final":[98],"RoIs":[101],"refined":[105],"Our":[107],"method":[108],"surpasses":[109],"existing":[110],"approaches":[111],"COCO":[114],"benchmark,":[115],"requiring":[116],"fewer":[117],"training":[118],"steps":[119],"less":[121],"memory":[122],"resources":[123],"due":[124],"dynamic":[127],"design":[128],"instance-aware":[130],"characteristic.":[131]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}