{"id":"https://openalex.org/W4312345337","doi":"https://doi.org/10.1109/indin51773.2022.9976099","title":"Multi-level Feature Reweighting and Fusion for Instance Segmentation","display_name":"Multi-level Feature Reweighting and Fusion for Instance Segmentation","publication_year":2022,"publication_date":"2022-07-25","ids":{"openalex":"https://openalex.org/W4312345337","doi":"https://doi.org/10.1109/indin51773.2022.9976099"},"language":"en","primary_location":{"id":"doi:10.1109/indin51773.2022.9976099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/indin51773.2022.9976099","pdf_url":null,"source":{"id":"https://openalex.org/S4363608444","display_name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","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/A5057436905","display_name":"Xuan-Thuy Vo","orcid":"https://orcid.org/0000-0002-7411-0697"},"institutions":[{"id":"https://openalex.org/I40542001","display_name":"University of Ulsan","ror":"https://ror.org/02c2f8975","country_code":"KR","type":"education","lineage":["https://openalex.org/I40542001"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Xuan-Thuy Vo","raw_affiliation_strings":["University of Ulsan,Electronic and Computer Engineering,Department of Electrical,Ulsan,South Korea,44610"],"affiliations":[{"raw_affiliation_string":"University of Ulsan,Electronic and Computer Engineering,Department of Electrical,Ulsan,South Korea,44610","institution_ids":["https://openalex.org/I40542001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060222649","display_name":"Tien-Dat Tran","orcid":"https://orcid.org/0000-0001-8266-0536"},"institutions":[{"id":"https://openalex.org/I40542001","display_name":"University of Ulsan","ror":"https://ror.org/02c2f8975","country_code":"KR","type":"education","lineage":["https://openalex.org/I40542001"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tien-Dat Tran","raw_affiliation_strings":["University of Ulsan,Electronic and Computer Engineering,Department of Electrical,Ulsan,South Korea,44610"],"affiliations":[{"raw_affiliation_string":"University of Ulsan,Electronic and Computer Engineering,Department of Electrical,Ulsan,South Korea,44610","institution_ids":["https://openalex.org/I40542001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079734356","display_name":"Duy-Linh Nguyen","orcid":"https://orcid.org/0000-0001-6184-4133"},"institutions":[{"id":"https://openalex.org/I40542001","display_name":"University of Ulsan","ror":"https://ror.org/02c2f8975","country_code":"KR","type":"education","lineage":["https://openalex.org/I40542001"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Duy-Linh Nguyen","raw_affiliation_strings":["University of Ulsan,Electronic and Computer Engineering,Department of Electrical,Ulsan,South Korea,44610"],"affiliations":[{"raw_affiliation_string":"University of Ulsan,Electronic and Computer Engineering,Department of Electrical,Ulsan,South Korea,44610","institution_ids":["https://openalex.org/I40542001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044448641","display_name":"Kang-Hyun Jo","orcid":"https://orcid.org/0000-0002-4937-7082"},"institutions":[{"id":"https://openalex.org/I40542001","display_name":"University of Ulsan","ror":"https://ror.org/02c2f8975","country_code":"KR","type":"education","lineage":["https://openalex.org/I40542001"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kang-Hyun Jo","raw_affiliation_strings":["University of Ulsan,Electronic and Computer Engineering,Department of Electrical,Ulsan,South Korea,44610"],"affiliations":[{"raw_affiliation_string":"University of Ulsan,Electronic and Computer Engineering,Department of Electrical,Ulsan,South Korea,44610","institution_ids":["https://openalex.org/I40542001"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057436905"],"corresponding_institution_ids":["https://openalex.org/I40542001"],"apc_list":null,"apc_paid":null,"fwci":0.0599,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.3085698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"28","issue":null,"first_page":"317","last_page":"322"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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":0.9991999864578247,"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":0.996999979019165,"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":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8003804683685303},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7078641653060913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6237695217132568},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6052019596099854},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6016097664833069},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5926076769828796},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5359702110290527},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.49789929389953613},{"id":"https://openalex.org/keywords/backbone-network","display_name":"Backbone network","score":0.4560515880584717},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4346785247325897},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43054455518722534},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.413019061088562},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2878810167312622}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8003804683685303},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7078641653060913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6237695217132568},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6052019596099854},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6016097664833069},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5926076769828796},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5359702110290527},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.49789929389953613},{"id":"https://openalex.org/C88796919","wikidata":"https://www.wikidata.org/wiki/Q1142907","display_name":"Backbone network","level":2,"score":0.4560515880584717},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4346785247325897},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43054455518722534},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.413019061088562},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2878810167312622},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/indin51773.2022.9976099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/indin51773.2022.9976099","pdf_url":null,"source":{"id":"https://openalex.org/S4363608444","display_name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 20th International Conference on Industrial Informatics (INDIN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1849277567","https://openalex.org/W1861492603","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2476548250","https://openalex.org/W2565639579","https://openalex.org/W2886701826","https://openalex.org/W2962721361","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963849369","https://openalex.org/W2963857746","https://openalex.org/W2993182889","https://openalex.org/W3034826836","https://openalex.org/W3093600664","https://openalex.org/W3094502228","https://openalex.org/W3113410735","https://openalex.org/W3177248696","https://openalex.org/W3185206247","https://openalex.org/W3205271623","https://openalex.org/W3205388591","https://openalex.org/W4205744321","https://openalex.org/W4226372493","https://openalex.org/W4288325606","https://openalex.org/W6620707391","https://openalex.org/W6639204139","https://openalex.org/W6684191040","https://openalex.org/W6764322716","https://openalex.org/W6784333009","https://openalex.org/W6784930956","https://openalex.org/W6797784111","https://openalex.org/W6806097638"],"related_works":["https://openalex.org/W2085033728","https://openalex.org/W4285411112","https://openalex.org/W2171299904","https://openalex.org/W1647606319","https://openalex.org/W2522537526","https://openalex.org/W4308659218","https://openalex.org/W2922442631","https://openalex.org/W4390494008","https://openalex.org/W2053596378","https://openalex.org/W2998228095"],"abstract_inverted_index":{"Accurate":[0],"instance":[1,190,248],"segmentation":[2,90,186,249],"requires":[3],"high-resolution":[4,15,33],"features":[5,47,53,71,78,86,148,156,171,180],"for":[6,192],"performing":[7],"a":[8,96,134,173,242,246],"dense":[9],"pixel-wise":[10],"prediction":[11],"task.":[12],"However,":[13],"using":[14,110],"feature":[16,39,100,139,197],"maps":[17],"results":[18],"in":[19,172,223],"highly":[20],"expensive":[21],"model":[22,91],"complexity":[23],"and":[24,51,59,76,94,112,160,176,226],"ineffective":[25],"receptive":[26],"fields.":[27],"To":[28,199],"overcome":[29],"the":[30,43,65,88,158,185,201,204,211,221],"problems":[31],"of":[32,157,203],"features,":[34],"conventional":[35],"methods":[36,105],"explore":[37],"multi-level":[38,99,179],"fusion":[40,101,164],"that":[41],"exchanges":[42],"information":[44,61,108],"between":[45],"low-level":[46,77],"at":[48,54,238],"earlier":[49],"layers":[50,120],"high-level":[52,70,147,196],"top":[55],"layers.":[56],"Both":[57],"low":[58],"high":[60],"is":[62,92,102,142,166],"extracted":[63],"by":[64,109],"hierarchical":[66],"backbone":[67],"network":[68,219],"where":[69],"contain":[72],"more":[73,80,97,117],"semantic":[74],"cues":[75],"encompass":[79],"specific":[81],"patterns.":[82],"Thus,":[83],"adopting":[84],"these":[85],"to":[87,121,144,168,188],"training":[89],"necessary,":[93],"designing":[95],"efficient":[98,163],"crucial.":[103],"Existing":[104],"balance":[106],"such":[107],"top-down":[111],"bottom-up":[113],"pathway":[114],"connections":[115],"with":[116],"inefficient":[118],"convolution":[119],"produce":[122],"richer":[123],"multi-scale":[124],"features.":[125],"In":[126],"this":[127],"work,":[128],"we":[129,207,231],"contribute":[130],"two":[131],"folds:":[132],"(1)":[133],"simple":[135,218],"but":[136],"effective":[137],"multilevel":[138],"reweighting":[140,152],"layer":[141],"proposed":[143,167,205],"strengthen":[145],"deep":[146],"based":[149],"on":[150,195,210,241],"channel":[151],"generated":[153],"from":[154],"multiple":[155],"backbone,":[159],"(2)":[161],"an":[162],"block":[165],"process":[169],"low-resolution":[170],"depth-to-spatial":[174],"manner":[175],"combine":[177],"enhanced":[178],"together.":[181],"These":[182],"designs":[183],"enable":[184],"models":[187],"predict":[189],"kernels":[191],"mask":[193],"generation":[194],"maps.":[198],"verify":[200],"effectiveness":[202],"method,":[206],"conduct":[208],"experiments":[209],"challenging":[212],"benchmark":[213],"dataset":[214],"MS-COCO.":[215],"Surprisingly,":[216],"our":[217],"outperforms":[220],"baseline":[222],"both":[224],"accuracy":[225],"inference":[227],"speed.":[228],"More":[229],"specifically,":[230],"achieve":[232],"35.4%":[233],"AP":[234],"<sup":[235],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[236],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">mask</sup>":[237],"19.5":[239],"FPS":[240],"GPU":[243],"device,":[244],"becoming":[245],"state-of-the-art":[247],"method.":[250]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}