{"id":"https://openalex.org/W3207759943","doi":"https://doi.org/10.1145/3474085.3475449","title":"Implicit Feature Refinement for Instance Segmentation","display_name":"Implicit Feature Refinement for Instance Segmentation","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3207759943","doi":"https://doi.org/10.1145/3474085.3475449","mag":"3207759943"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475449","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","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/A5053215437","display_name":"Lufan Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lufan Ma","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110647238","display_name":"Tiancai Wang","orcid":"https://orcid.org/0009-0001-6517-4293"},"institutions":[{"id":"https://openalex.org/I4401726805","display_name":"Megvii (China)","ror":"https://ror.org/040b32p69","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726805"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiancai Wang","raw_affiliation_strings":["MEGVII Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MEGVII Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726805"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035683291","display_name":"Bin Dong","orcid":"https://orcid.org/0000-0003-1295-3362"},"institutions":[{"id":"https://openalex.org/I4401726805","display_name":"Megvii (China)","ror":"https://ror.org/040b32p69","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726805"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Dong","raw_affiliation_strings":["MEGVII Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MEGVII Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726805"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013716631","display_name":"Jiangpeng Yan","orcid":"https://orcid.org/0000-0002-0767-1726"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangpeng Yan","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100754504","display_name":"Xiu Li","orcid":"https://orcid.org/0000-0003-0403-1923"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiu Li","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362465","display_name":"Xiangyu Zhang","orcid":"https://orcid.org/0000-0003-2138-4608"},"institutions":[{"id":"https://openalex.org/I4401726805","display_name":"Megvii (China)","ror":"https://ror.org/040b32p69","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726805"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhang","raw_affiliation_strings":["MEGVII Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MEGVII Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726805"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2911,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.56871663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3088","last_page":"3096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8066117763519287},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6825172901153564},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6470787525177002},{"id":"https://openalex.org/keywords/iterated-function","display_name":"Iterated function","score":0.6158279180526733},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5937272906303406},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5807029604911804},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.434770405292511},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4249572455883026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.388680100440979},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35423213243484497},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.18146705627441406},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14241743087768555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8066117763519287},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6825172901153564},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6470787525177002},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.6158279180526733},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5937272906303406},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5807029604911804},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.434770405292511},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4249572455883026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.388680100440979},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35423213243484497},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.18146705627441406},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14241743087768555},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475449","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1881179843","https://openalex.org/W1903029394","https://openalex.org/W2007431958","https://openalex.org/W2116628315","https://openalex.org/W2132868735","https://openalex.org/W2194775991","https://openalex.org/W2768489488","https://openalex.org/W2795783309","https://openalex.org/W2808746463","https://openalex.org/W2920326761","https://openalex.org/W2953106684","https://openalex.org/W2963016848","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W2963849369","https://openalex.org/W2964241181","https://openalex.org/W2964330624","https://openalex.org/W2971842688","https://openalex.org/W2982723417","https://openalex.org/W3012846999","https://openalex.org/W3034428102","https://openalex.org/W3034499084","https://openalex.org/W3035396860","https://openalex.org/W3096609285","https://openalex.org/W3106546328","https://openalex.org/W3106651317","https://openalex.org/W3113410735","https://openalex.org/W3119630632","https://openalex.org/W3171015922","https://openalex.org/W3172752666","https://openalex.org/W3200539537","https://openalex.org/W6603242443"],"related_works":["https://openalex.org/W2560215812","https://openalex.org/W3103325625","https://openalex.org/W2949601986","https://openalex.org/W1486898455","https://openalex.org/W2788972299","https://openalex.org/W2498789492","https://openalex.org/W2521347458","https://openalex.org/W2729981612","https://openalex.org/W3209312100","https://openalex.org/W2890372105"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,110,146],"novel":[3],"implicit":[4,86,95],"feature":[5,87],"refinement":[6,41,88,123],"module":[7,149],"for":[8,68],"high-quality":[9],"instance":[10,14,24,101,137,174],"segmentation.":[11],"Existing":[12],"image/video":[13,173],"segmentation":[15,175],"methods":[16],"rely":[17],"on":[18,82,158,171,186],"explicitly":[19],"stacked":[20],"convolutions":[21,50],"to":[22,77,152],"refine":[23],"features":[25,102,138],"before":[26],"the":[27,46,71,85,159,179],"final":[28],"prediction.":[29],"In":[30],"this":[31,83],"paper,":[32],"we":[33],"first":[34],"give":[35],"an":[36,55,78,94,121],"empirical":[37],"comparison":[38],"of":[39,100,129,139],"different":[40],"strategies,":[42],"which":[43],"reveals":[44],"that":[45,165],"widely-used":[47],"four":[48],"consecutive":[49],"are":[51],"not":[52],"necessary.":[53],"As":[54],"alternative,":[56],"weight-sharing":[57],"convolution":[58],"blocks":[59],"provides":[60],"competitive":[61],"performance.":[62],"When":[63],"such":[64],"block":[65,72],"is":[66,90],"iterated":[67],"infinite":[69],"times,":[70],"output":[73],"will":[74,197],"eventually":[75],"converge":[76],"equilibrium":[79,98,136],"state.":[80],"Based":[81],"observation,":[84],"(IFR)":[89],"developed":[91],"by":[92,106],"constructing":[93],"function.":[96],"The":[97],"state":[99],"can":[103],"be":[104,198],"obtained":[105],"fixed-point":[107],"iteration":[108],"via":[109],"simulated":[111],"infinite-depth":[112,122],"network.":[113],"Our":[114],"IFR":[115,167],"enjoys":[116],"several":[117],"advantages:":[118],"1)":[119],"simulates":[120],"network":[124],"while":[125,177],"only":[126,190],"requiring":[127],"parameters":[128,192],"single":[130],"residual":[131],"block;":[132],"2)":[133],"produces":[134],"high-level":[135],"global":[140],"receptive":[141],"field;":[142],"3)":[143],"serves":[144],"as":[145],"plug-and-play":[147],"general":[148],"easily":[150],"extended":[151],"most":[153],"object":[154],"recognition":[155],"frameworks.":[156],"Experiments":[157],"COCO":[160],"and":[161],"YouTube-VIS":[162],"benchmarks":[163],"show":[164],"our":[166],"achieves":[168],"improved":[169],"performance":[170],"state-of-the-art":[172],"frameworks,":[176],"reducing":[178],"parameter":[180],"burden":[181],"(e.g.":[182],"1%":[183],"AP":[184],"improvement":[185],"Mask":[187],"R-CNN":[188],"with":[189],"30.0%":[191],"in":[193],"mask":[194],"head).":[195],"Code":[196],"made":[199],"available":[200],"at":[201],"\\hrefhttps://github.com/lufanma/IFR.git":[202],"https://github.com/lufanma/IFR.git":[203],".":[204]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}