{"id":"https://openalex.org/W4281661976","doi":"https://doi.org/10.1109/ipta54936.2022.9784143","title":"On the relevance of edge-conditioned convolution for GNN-based semantic image segmentation using spatial relationships","display_name":"On the relevance of edge-conditioned convolution for GNN-based semantic image segmentation using spatial relationships","publication_year":2022,"publication_date":"2022-04-19","ids":{"openalex":"https://openalex.org/W4281661976","doi":"https://doi.org/10.1109/ipta54936.2022.9784143"},"language":"en","primary_location":{"id":"doi:10.1109/ipta54936.2022.9784143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipta54936.2022.9784143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Eleventh International Conference on Image Processing Theory, Tools and Applications (IPTA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-03830071","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030212203","display_name":"Patty Coupeau","orcid":"https://orcid.org/0000-0003-0164-5540"},"institutions":[{"id":"https://openalex.org/I49451733","display_name":"Universit\u00e9 d'Angers","ror":"https://ror.org/04yrqp957","country_code":"FR","type":"education","lineage":["https://openalex.org/I49451733"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"P. Coupeau","raw_affiliation_strings":["Université d'Angers,LARIS SFR MATHSTIC,Angers,France,F-49000"],"raw_orcid":"https://orcid.org/0000-0003-0164-5540","affiliations":[{"raw_affiliation_string":"Université d'Angers,LARIS SFR MATHSTIC,Angers,France,F-49000","institution_ids":["https://openalex.org/I49451733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053520474","display_name":"Jean-Baptiste Fasquel","orcid":"https://orcid.org/0000-0001-9183-0365"},"institutions":[{"id":"https://openalex.org/I49451733","display_name":"Universit\u00e9 d'Angers","ror":"https://ror.org/04yrqp957","country_code":"FR","type":"education","lineage":["https://openalex.org/I49451733"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"J.-B. Fasquel","raw_affiliation_strings":["Université d'Angers,LARIS SFR MATHSTIC,Angers,France,F-49000"],"raw_orcid":"https://orcid.org/0000-0001-9183-0365","affiliations":[{"raw_affiliation_string":"Université d'Angers,LARIS SFR MATHSTIC,Angers,France,F-49000","institution_ids":["https://openalex.org/I49451733"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036199505","display_name":"M. Dinomais","orcid":"https://orcid.org/0000-0002-6980-1178"},"institutions":[{"id":"https://openalex.org/I4210112910","display_name":"Centre Hospitalier Universitaire d'Angers","ror":"https://ror.org/0250ngj72","country_code":"FR","type":"healthcare","lineage":["https://openalex.org/I4210112910"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"M. Dinomais","raw_affiliation_strings":["Université d'Angers, Centre Hospitalier Universitaire d'Angers,LARIS, SFR MATHSTIC,Département de médecine physique et de réadaptation,France"],"raw_orcid":"https://orcid.org/0000-0002-6980-1178","affiliations":[{"raw_affiliation_string":"Université d'Angers, Centre Hospitalier Universitaire d'Angers,LARIS, SFR MATHSTIC,Département de médecine physique et de réadaptation,France","institution_ids":["https://openalex.org/I4210112910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5030212203"],"corresponding_institution_ids":["https://openalex.org/I49451733"],"apc_list":null,"apc_paid":null,"fwci":0.3346,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.56762224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9958999752998352,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9955000281333923,"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":0.7489064931869507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6519880294799805},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6490083336830139},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6305187344551086},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5199307799339294},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5184433460235596},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.49821972846984863},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4499751031398773},{"id":"https://openalex.org/keywords/hausdorff-distance","display_name":"Hausdorff distance","score":0.4479316771030426},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4115133583545685},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.17039987444877625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7489064931869507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6519880294799805},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6490083336830139},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6305187344551086},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5199307799339294},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5184433460235596},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49821972846984863},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4499751031398773},{"id":"https://openalex.org/C141898687","wikidata":"https://www.wikidata.org/wiki/Q1501997","display_name":"Hausdorff distance","level":2,"score":0.4479316771030426},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4115133583545685},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.17039987444877625}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipta54936.2022.9784143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipta54936.2022.9784143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Eleventh International Conference on Image Processing Theory, Tools and Applications (IPTA)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03830071v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03830071","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2022 Eleventh International Conference on Image Processing Theory, Tools and Applications (IPTA), Apr 2022, Salzburg, Austria. pp.1-6, ⟨10.1109/IPTA54936.2022.9784143⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03830071v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03830071","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2022 Eleventh International Conference on Image Processing Theory, Tools and Applications (IPTA), Apr 2022, Salzburg, Austria. pp.1-6, ⟨10.1109/IPTA54936.2022.9784143⟩","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2124465992","https://openalex.org/W2132513126","https://openalex.org/W2332001143","https://openalex.org/W2606202972","https://openalex.org/W2799132636","https://openalex.org/W2801783281","https://openalex.org/W2804860796","https://openalex.org/W2964015378","https://openalex.org/W2997785591","https://openalex.org/W3011667710","https://openalex.org/W3053379555","https://openalex.org/W3099141824","https://openalex.org/W3118358609","https://openalex.org/W3173612122","https://openalex.org/W3210259784","https://openalex.org/W3217037671","https://openalex.org/W4206241865","https://openalex.org/W6639824700","https://openalex.org/W6726873649","https://openalex.org/W6788142248","https://openalex.org/W6796890914"],"related_works":["https://openalex.org/W2136359393","https://openalex.org/W3125779006","https://openalex.org/W4383558899","https://openalex.org/W4293226380","https://openalex.org/W4383558898","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W3029198973"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,52,70,114,130,143,158,167],"fundamental":[4],"task":[5,123],"of":[6,96,116,124,142,177],"semantic":[7],"image":[8,17],"segmentation":[9],"by":[10,51,145,156,172],"exploiting":[11],"structural":[12,45],"information":[13,46],"(spatial":[14],"relationships":[15],"between":[16],"regions).":[18],"To":[19],"perform":[20],"such":[21],"task,":[22],"we":[23],"propose":[24],"to":[25,48,56,104,107,120],"combine":[26],"a":[27,43,60,89,93,121,133],"deep":[28,117],"neural":[29,65],"network":[30,66],"(CNN)":[31],"with":[32,163,174],"inexact":[33],"\u201cmany-to-one-or-none\u201d":[34],"graph":[35,64,125],"matching":[36],"where":[37],"graphs":[38],"encode":[39],"efficiently":[40],"class":[41],"probabilities":[42],"nd":[44],"related":[47],"regions":[49],"segmented":[50],"CNN.":[53],"In":[54],"order":[55],"achieve":[57],"node":[58,77],"classification,":[59],"basic":[61],"2":[62],"-layer":[63],"(GNN)":[67],"based":[68],"on":[69,87,136,151],"edge-conditioned":[71],"convolution":[72],"operator":[73],"(ECConv),":[74],"managing":[75],"both":[76,88],"and":[78,92,139,171],"edge":[79],"attributes,":[80],"is":[81,102],"considered.":[82],"Prelim-inary":[83],"experiments":[84],"are":[85],"performed":[86],"synthetic":[90,137],"dataset":[91,95,138,170],"public":[94],"face":[97],"images":[98],"(FASSEG).":[99],"Our":[100],"approach":[101],"shown":[103],"be":[105],"resilient":[106],"small":[108],"training":[109,169,178],"datasets":[110],"that":[111,129],"often":[112],"limit":[113],"performance":[115,141],"learning":[118],"thanks":[119],"preprocessing":[122],"coarsening.":[126],"Results":[127],"show":[128],"proposal":[131],"reaches":[132],"perfect":[134],"accuracy":[135],"improves":[140],"CNN":[144,164],"6%":[146],"(bounding":[147],"box":[148],"dice":[149],"index)":[150],"FASSEG.":[152],"Moreover,":[153],"it":[154],"enhances":[155],"27%":[157],"initial":[159],"Hausdorff":[160],"distance":[161],"(i.e.":[162],"only)":[165],"using":[166],"entire":[168],"41%":[173],"only":[175],"75%":[176],"samples.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}