{"id":"https://openalex.org/W4313190041","doi":"https://doi.org/10.1109/icpr56361.2022.9956326","title":"Graph Laplacian Regularization based on the Differences of Neighboring Pixels for Conditional Convolutions for Instance Segmentation","display_name":"Graph Laplacian Regularization based on the Differences of Neighboring Pixels for Conditional Convolutions for Instance Segmentation","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4313190041","doi":"https://doi.org/10.1109/icpr56361.2022.9956326"},"language":"en","primary_location":{"id":"doi:10.1109/icpr56361.2022.9956326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956326","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5063371211","display_name":"Shinji Uchinoura","orcid":null},"institutions":[{"id":"https://openalex.org/I183792356","display_name":"Hiroshima University of Economics","ror":"https://ror.org/027b58k10","country_code":"JP","type":"education","lineage":["https://openalex.org/I183792356"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinji Uchinoura","raw_affiliation_strings":["Hiroshima University,Japan","Hiroshima University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hiroshima University,Japan","institution_ids":["https://openalex.org/I183792356"]},{"raw_affiliation_string":"Hiroshima University, Japan","institution_ids":["https://openalex.org/I183792356"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086456461","display_name":"Takio Kurita","orcid":"https://orcid.org/0000-0003-3982-6750"},"institutions":[{"id":"https://openalex.org/I183792356","display_name":"Hiroshima University of Economics","ror":"https://ror.org/027b58k10","country_code":"JP","type":"education","lineage":["https://openalex.org/I183792356"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takio Kurita","raw_affiliation_strings":["Hiroshima University,Japan","Hiroshima University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hiroshima University,Japan","institution_ids":["https://openalex.org/I183792356"]},{"raw_affiliation_string":"Hiroshima University, Japan","institution_ids":["https://openalex.org/I183792356"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183792356"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":null,"first_page":"3611","last_page":"3617"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9980999827384949,"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/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.7969909906387329},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.7683124542236328},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6967854499816895},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.693587064743042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.646640419960022},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5354383587837219},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.520818829536438},{"id":"https://openalex.org/keywords/cut","display_name":"Cut","score":0.5203163623809814},{"id":"https://openalex.org/keywords/laplace-operator","display_name":"Laplace operator","score":0.4890314042568207},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4881359040737152},{"id":"https://openalex.org/keywords/dice","display_name":"Dice","score":0.45733150839805603},{"id":"https://openalex.org/keywords/image-resolution","display_name":"Image resolution","score":0.41730836033821106},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3852902054786682},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2746073603630066},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.16933465003967285}],"concepts":[{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.7969909906387329},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7683124542236328},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6967854499816895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.693587064743042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.646640419960022},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5354383587837219},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.520818829536438},{"id":"https://openalex.org/C5134670","wikidata":"https://www.wikidata.org/wiki/Q1626444","display_name":"Cut","level":4,"score":0.5203163623809814},{"id":"https://openalex.org/C165700671","wikidata":"https://www.wikidata.org/wiki/Q203484","display_name":"Laplace operator","level":2,"score":0.4890314042568207},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4881359040737152},{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.45733150839805603},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.41730836033821106},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3852902054786682},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2746073603630066},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.16933465003967285},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr56361.2022.9956326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956326","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1677182931","https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W2108598243","https://openalex.org/W2140514146","https://openalex.org/W2194775991","https://openalex.org/W2317851288","https://openalex.org/W2340897893","https://openalex.org/W2555182955","https://openalex.org/W2565639579","https://openalex.org/W2734349601","https://openalex.org/W2920326761","https://openalex.org/W2962766617","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963849369","https://openalex.org/W2963927307","https://openalex.org/W2982161360","https://openalex.org/W2982770724","https://openalex.org/W2990361805","https://openalex.org/W2993182889","https://openalex.org/W3034681942","https://openalex.org/W3034826836","https://openalex.org/W3035049382","https://openalex.org/W3103253084","https://openalex.org/W3106546328","https://openalex.org/W3110416571","https://openalex.org/W4200078761","https://openalex.org/W6628973269","https://openalex.org/W6639102338","https://openalex.org/W6699915822","https://openalex.org/W6730003152","https://openalex.org/W6760424586","https://openalex.org/W6805142713"],"related_works":["https://openalex.org/W3104750253","https://openalex.org/W3021239166","https://openalex.org/W2586273397","https://openalex.org/W2390936256","https://openalex.org/W2483429559","https://openalex.org/W2016385589","https://openalex.org/W2009559548","https://openalex.org/W2890643743","https://openalex.org/W4366341510","https://openalex.org/W2906397153"],"abstract_inverted_index":{"We":[0,102,156],"propose":[1,135],"a":[2,24,55,73,136,147,172],"simple":[3],"and":[4,58,97,113,161,182,189],"effective":[5],"regularization":[6,137,164],"method":[7],"for":[8],"instance":[9],"segmentation,":[10],"GLRDN-L2":[11],"(Graph":[12],"Laplacian":[13],"Regularization":[14],"based":[15,75],"on":[16,76,186],"Differences":[17],"of":[18,87,150,171],"Neighboring":[19],"Pixels).":[20],"Instance":[21],"segmentation":[22],"is":[23],"challenging":[25],"task":[26],"in":[27,99,117,127,142,165],"computer":[28],"vision.":[29],"For":[30],"many":[31],"years,":[32],"ROI-based":[33],"methods":[34,71],"such":[35,79,93],"as":[36,54,80,94],"Mask":[37,64],"R-CNN":[38],"have":[39],"dominantly":[40],"presented":[41],"the":[42,46,85,100,110,118,128,140,143,151,169,179],"top":[43],"performances;":[44],"however,":[45],"recently":[47],"proposed":[48],"CondInst,":[49],"which":[50],"employs":[51],"dynamic":[52],"FCNs":[53],"mask":[56,61],"head":[57],"performs":[59],"instance-aware":[60],"prediction,":[62],"outperforms":[63],"R-CNN.":[65],"To":[66,130],"our":[67,163],"best":[68],"knowledge,":[69],"all":[70],"optimize":[72],"model":[74],"pixel-wise":[77],"losses":[78],"Dice":[81],"Loss.":[82],"Even":[83],"with":[84,146,160],"results":[86],"high-resolution":[88],"masks,":[89],"there":[90],"are":[91,107],"problems":[92,106],"blurred":[95],"boundaries":[96],"hollows":[98],"instances.":[101],"assume":[103],"that":[104,138,175],"these":[105,132],"due":[108],"to":[109,167,178],"spatial":[111,144],"structure":[112,145],"contextual":[114],"information":[115],"contained":[116],"relationships":[119],"between":[120,153],"neighboring":[121,154],"pixels":[122],"not":[123],"being":[124],"incorporated":[125],"well":[126],"model.":[129],"address":[131],"problems,":[133],"we":[134],"penalizes":[139],"errors":[141],"graph":[148],"composed":[149],"differences":[152],"pixels.":[155],"compare":[157],"models":[158],"trained":[159],"without":[162],"CondInst":[166],"validate":[168],"effect":[170],"natural":[173],"extension":[174],"adds":[176],"differentiation":[177],"loss":[180],"function":[181],"demonstrate":[183],"performance":[184],"improvement":[185],"both":[187],"COCO":[188],"Cityscapes":[190],"datasets.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}