{"id":"https://openalex.org/W4392931179","doi":"https://doi.org/10.1109/icassp48485.2024.10447191","title":"Diffusioninst: Diffusion Model for Instance Segmentation","display_name":"Diffusioninst: Diffusion Model for Instance Segmentation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392931179","doi":"https://doi.org/10.1109/icassp48485.2024.10447191"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5101878836","display_name":"Zhangxuan Gu","orcid":"https://orcid.org/0000-0002-2102-2693"},"institutions":[{"id":"https://openalex.org/I4210087087","display_name":"Henan Tianguan Group (China)","ror":"https://ror.org/001rfde81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087087"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhangxuan Gu","raw_affiliation_strings":["Ant Group Inc.,Tiansuan Lab","Tiansuan Lab, Ant Group Inc"],"affiliations":[{"raw_affiliation_string":"Ant Group Inc.,Tiansuan Lab","institution_ids":["https://openalex.org/I4210087087"]},{"raw_affiliation_string":"Tiansuan Lab, Ant Group Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045279290","display_name":"Haoxing Chen","orcid":"https://orcid.org/0000-0001-6637-8741"},"institutions":[{"id":"https://openalex.org/I4210087087","display_name":"Henan Tianguan Group (China)","ror":"https://ror.org/001rfde81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087087"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoxing Chen","raw_affiliation_strings":["Ant Group Inc.,Tiansuan Lab","Tiansuan Lab, Ant Group Inc"],"affiliations":[{"raw_affiliation_string":"Ant Group Inc.,Tiansuan Lab","institution_ids":["https://openalex.org/I4210087087"]},{"raw_affiliation_string":"Tiansuan Lab, Ant Group Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056204625","display_name":"Zhuoer Xu","orcid":"https://orcid.org/0009-0000-4316-5364"},"institutions":[{"id":"https://openalex.org/I4210087087","display_name":"Henan Tianguan Group (China)","ror":"https://ror.org/001rfde81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087087"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoer Xu","raw_affiliation_strings":["Ant Group Inc.,Tiansuan Lab","Tiansuan Lab, Ant Group Inc"],"affiliations":[{"raw_affiliation_string":"Ant Group Inc.,Tiansuan Lab","institution_ids":["https://openalex.org/I4210087087"]},{"raw_affiliation_string":"Tiansuan Lab, Ant Group Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101878836"],"corresponding_institution_ids":["https://openalex.org/I4210087087"],"apc_list":null,"apc_paid":null,"fwci":11.9592,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.99179898,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2730","last_page":"2734"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9980999827384949,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996399998664856,"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":0.7652984857559204},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6888916492462158},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6189662218093872},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6125136017799377},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5596814155578613},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5587975382804871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5295021533966064},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5010843276977539},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4755420684814453},{"id":"https://openalex.org/keywords/image-denoising","display_name":"Image denoising","score":0.4278448820114136},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.41309720277786255},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.41171708703041077},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.38103288412094116},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3674112558364868},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06350496411323547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7652984857559204},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6888916492462158},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6189662218093872},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6125136017799377},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5596814155578613},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5587975382804871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5295021533966064},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5010843276977539},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4755420684814453},{"id":"https://openalex.org/C2983327147","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Image denoising","level":3,"score":0.4278448820114136},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.41309720277786255},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.41171708703041077},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.38103288412094116},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3674112558364868},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06350496411323547},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2948672349","https://openalex.org/W2962914239","https://openalex.org/W2963150697","https://openalex.org/W2963857746","https://openalex.org/W2983943451","https://openalex.org/W2993182889","https://openalex.org/W3034428102","https://openalex.org/W3034681942","https://openalex.org/W3034826836","https://openalex.org/W3036167779","https://openalex.org/W3093600664","https://openalex.org/W3106546328","https://openalex.org/W3113410735","https://openalex.org/W3138516171","https://openalex.org/W3168783492","https://openalex.org/W3172971995","https://openalex.org/W4214613769","https://openalex.org/W4226000809","https://openalex.org/W4312815172","https://openalex.org/W4386071535","https://openalex.org/W4390873752","https://openalex.org/W6779823529","https://openalex.org/W6784930956","https://openalex.org/W6786375611","https://openalex.org/W6796402304","https://openalex.org/W6804703708"],"related_works":["https://openalex.org/W1522196789","https://openalex.org/W2087258800","https://openalex.org/W2810018092","https://openalex.org/W2387428419","https://openalex.org/W4401571043","https://openalex.org/W2098237619","https://openalex.org/W1974034585","https://openalex.org/W4312627788","https://openalex.org/W2353444452","https://openalex.org/W2001438600"],"abstract_inverted_index":{"Diffusion":[0],"frameworks":[1],"have":[2],"achieved":[3],"comparable":[4],"performance":[5],"with":[6,59],"previous":[7],"state-of-the-art":[8],"image":[9],"generation":[10],"models.":[11],"This":[12],"paper":[13],"proposes":[14],"DiffusionInst,":[15],"a":[16,28,50],"novel":[17],"framework":[18],"representing":[19],"instances":[20],"as":[21,27,54],"vectors":[22],"and":[23,56,69],"formulates":[24],"instance":[25],"segmentation":[26],"noise-to-vector":[29],"denoising":[30,61],"process.":[31],"The":[32],"model":[33],"is":[34,79],"trained":[35],"to":[36],"reverse":[37],"the":[38],"noisy":[39],"groundtruth":[40],"mask":[41,58],"without":[42],"any":[43],"inductive":[44],"bias":[45],"from":[46],"RPN.":[47],"It":[48],"takes":[49],"randomly":[51],"generated":[52],"vector":[53],"input":[55],"outputs":[57],"multi-step":[60],"during":[62],"inference.":[63],"Extensive":[64],"experimental":[65],"results":[66],"on":[67],"COCO":[68],"LVIS":[70],"show":[71],"that":[72],"DiffusionInst":[73],"achieves":[74],"competitive":[75],"performance.":[76],"Our":[77],"code":[78],"available":[80],"at":[81],"https://github.com/chenhaoxing/DiffusionInst.":[82]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":15}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}