{"id":"https://openalex.org/W4321192253","doi":"https://doi.org/10.1109/icce56470.2023.10043389","title":"Top-K Confidence Map Aggregation for Robust Semantic Segmentation Against Unexpected Degradation","display_name":"Top-K Confidence Map Aggregation for Robust Semantic Segmentation Against Unexpected Degradation","publication_year":2023,"publication_date":"2023-01-06","ids":{"openalex":"https://openalex.org/W4321192253","doi":"https://doi.org/10.1109/icce56470.2023.10043389"},"language":"en","primary_location":{"id":"doi:10.1109/icce56470.2023.10043389","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icce56470.2023.10043389","pdf_url":null,"source":{"id":"https://openalex.org/S4363607959","display_name":"2023 IEEE International Conference on Consumer Electronics (ICCE)","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":"2023 IEEE International Conference on Consumer Electronics (ICCE)","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/A5000077459","display_name":"Yu Moriyasu","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yu Moriyasu","raw_affiliation_strings":["School of Engineering, Tokyo Institute of Technology,Tokyo,Japan","School of Engineering, Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Tokyo Institute of Technology,Tokyo,Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"School of Engineering, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010157078","display_name":"Takashi Shibata","orcid":"https://orcid.org/0000-0001-8072-3847"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Shibata","raw_affiliation_strings":["NTT Corporation,Communication Science Laboratories,Tokyo,Japan","Communication Science Laboratories, NTT Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Communication Science Laboratories,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"Communication Science Laboratories, NTT Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040292386","display_name":"Masayuki Tanaka","orcid":"https://orcid.org/0000-0002-5756-1904"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayuki Tanaka","raw_affiliation_strings":["School of Engineering, Tokyo Institute of Technology,Tokyo,Japan","School of Engineering, Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Tokyo Institute of Technology,Tokyo,Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"School of Engineering, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024453747","display_name":"Masatoshi Okutomi","orcid":"https://orcid.org/0000-0001-5787-0742"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masatoshi Okutomi","raw_affiliation_strings":["School of Engineering, Tokyo Institute of Technology,Tokyo,Japan","School of Engineering, Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Tokyo Institute of Technology,Tokyo,Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"School of Engineering, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9961000084877014,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.995199978351593,"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":0.798068642616272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7245504260063171},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6551703214645386},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.64656001329422},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5357797145843506},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5138771533966064},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5055439472198486},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5035452246665955},{"id":"https://openalex.org/keywords/degradation","display_name":"Degradation (telecommunications)","score":0.4679521322250366},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4276583790779114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.798068642616272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7245504260063171},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6551703214645386},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.64656001329422},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5357797145843506},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5138771533966064},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5055439472198486},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5035452246665955},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.4679521322250366},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4276583790779114},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icce56470.2023.10043389","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icce56470.2023.10043389","pdf_url":null,"source":{"id":"https://openalex.org/S4363607959","display_name":"2023 IEEE International Conference on Consumer Electronics (ICCE)","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":"2023 IEEE International Conference on Consumer Electronics (ICCE)","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":31,"referenced_works":["https://openalex.org/W1913356549","https://openalex.org/W2171943915","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2395611524","https://openalex.org/W2508457857","https://openalex.org/W2736282206","https://openalex.org/W2884367402","https://openalex.org/W2895874132","https://openalex.org/W2907965334","https://openalex.org/W2963299736","https://openalex.org/W2963881378","https://openalex.org/W2964097310","https://openalex.org/W2964254867","https://openalex.org/W2970213471","https://openalex.org/W3028392891","https://openalex.org/W3035358681","https://openalex.org/W3089816516","https://openalex.org/W3090773703","https://openalex.org/W3093088410","https://openalex.org/W3108281323","https://openalex.org/W3112027556","https://openalex.org/W3165745140","https://openalex.org/W4214592090","https://openalex.org/W4242059867","https://openalex.org/W6748481559","https://openalex.org/W6767361312","https://openalex.org/W6774725951","https://openalex.org/W6778231270","https://openalex.org/W6787322260","https://openalex.org/W6797399245"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W2055243143","https://openalex.org/W2534928293","https://openalex.org/W4313906399","https://openalex.org/W4321487865","https://openalex.org/W2150099345","https://openalex.org/W2811106690","https://openalex.org/W4239306820","https://openalex.org/W2947043951","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"have":[4,17],"become":[5],"the":[6,20,34,48,66,86,96,106,118,131,134,151],"mainstream":[7],"for":[8,28,179],"computer":[9],"vision":[10],"tasks":[11],"like":[12],"semantic":[13,23,87,98],"segmentation.":[14,24],"The":[15,25,63],"CNNs":[16],"substantially":[18],"improved":[19],"performance":[21,64,165],"of":[22,65,115],"implicit":[26],"assumption":[27],"those":[29,74],"CNN":[30,68],"approaches":[31],"is":[32,37,70,104,109,137,173],"that":[33,84,105,170],"input":[35,49,135],"image":[36,41,50,54,76,92,108,136],"clean":[38],"without":[39,94],"any":[40],"degradation.":[42],"In":[43,130],"an":[44],"actual":[45],"situation,":[46],"however,":[47],"contains":[51],"many":[52],"unexpected":[53,75],"degradations":[55,182],"such":[56],"as":[57],"noise,":[58],"blur,":[59],"or":[60],"compression":[61],"distortion.":[62],"conventional":[67],"approach":[69],"severely":[71],"degraded":[72],"by":[73],"degradations.":[77],"This":[78],"paper":[79],"presents":[80],"a":[81,124,158,184],"simple":[82],"framework":[83,172],"makes":[85],"segmentation":[88,99],"algorithms":[89],"robust":[90,175],"against":[91],"degradation":[93,116],"re-training":[95],"original":[97],"CNN.":[100],"Our":[101],"key":[102],"observation":[103],"down-sampled":[107,139],"less":[110],"sensitive":[111],"to":[112,149,163],"various":[113],"types":[114],"than":[117,176],"original-sized":[119],"image.":[120],"Therefore,":[121],"we":[122],"adopt":[123],"multi-scale":[125,132],"test":[126],"time":[127],"augmentation":[128],"(TTA).":[129],"TTA,":[133],"firstly":[138],"with":[140,181,188],"multiple":[141],"scales.":[142],"Then,":[143],"inferred":[144],"confidence":[145,160],"maps":[146],"are":[147],"aggregated":[148],"obtain":[150],"final":[152],"inference":[153],"result.":[154],"We":[155],"also":[156],"propose":[157],"top-K":[159],"map":[161],"aggregation":[162],"further":[164],"improvement.":[166],"Experimental":[167],"results":[168],"demonstrate":[169],"our":[171],"more":[174],"existing":[177],"methods":[178],"images":[180],"and":[183],"real":[185],"compressed":[186],"video":[187],"H.264.":[189]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}