{"id":"https://openalex.org/W2964096383","doi":"https://doi.org/10.48550/arxiv.1505.07293","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling","display_name":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling","publication_year":2015,"publication_date":"2015-05-27","ids":{"openalex":"https://openalex.org/W2964096383","doi":"https://doi.org/10.48550/arxiv.1505.07293","mag":"2964096383"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1505.07293","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1505.07293","pdf_url":"https://arxiv.org/pdf/1505.07293","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1505.07293","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084236726","display_name":"Vijay Badrinarayanan","orcid":"https://orcid.org/0000-0002-3297-7495","observed_orcids":["https://orcid.org/0000-0002-3297-7495"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Badrinarayanan, Vijay","raw_affiliation_strings":["Machine Intelligence Lab , Department of Engineering , University of Cambridge , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Intelligence Lab , Department of Engineering , University of Cambridge , UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055942061","display_name":"Ankur Handa","orcid":"https://orcid.org/0000-0001-5170-1323","observed_orcids":["https://orcid.org/0000-0001-5170-1323"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Handa, Ankur","raw_affiliation_strings":["Machine Intelligence Lab , Department of Engineering , University of Cambridge , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Intelligence Lab , Department of Engineering , University of Cambridge , UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018207993","display_name":"Roberto Cipolla","orcid":"https://orcid.org/0000-0002-8999-2151","observed_orcids":["https://orcid.org/0000-0002-8999-2151"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cipolla, Roberto","raw_affiliation_strings":["Machine Intelligence Lab , Department of Engineering , University of Cambridge , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Intelligence Lab , Department of Engineering , University of Cambridge , UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":285,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9932000041007996,"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":0.9932000041007996,"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":0.003000000026077032,"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"}},{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.0020000000949949026,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segnet","display_name":"SegNet","score":0.9610000252723694},{"id":"https://openalex.org/keywords/semantic-segmentation","display_name":"semantic segmentation","score":0.9290000200271606},{"id":"https://openalex.org/keywords/encoder-decoder-architecture","display_name":"encoder-decoder architecture","score":0.9509999752044678},{"id":"https://openalex.org/keywords/feature-upsampling","display_name":"feature upsampling","score":0.6669999957084656},{"id":"https://openalex.org/keywords/spatial-context","display_name":"spatial context","score":0.8840000033378601},{"id":"https://openalex.org/keywords/deep-convolutional-neural-networks","display_name":"deep convolutional neural networks","score":0.5270000100135803},{"id":"https://openalex.org/keywords/outdoor-scenes","display_name":"outdoor scenes","score":0.36899998784065247},{"id":"https://openalex.org/keywords/indoor-scenes","display_name":"indoor scenes","score":0.871999979019165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7507117986679077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7364122271537781},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6840014457702637},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6625380516052246},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.65353924036026},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6097882986068726},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6040773391723633},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5407090783119202},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5196453332901001},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4947158992290497},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4831487536430359},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.4784300923347473},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.45894303917884827},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.4251341223716736},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.23651519417762756},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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":4,"locations":[{"id":"pmh:oai:arXiv.org:1505.07293","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1505.07293","pdf_url":"https://arxiv.org/pdf/1505.07293","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1505.07293","doi":"https://doi.org/10.48550/arxiv.1505.07293","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1505.07293","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2964096383","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1505.07293","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"mag:360623563","doi":null,"is_oa":false,"landing_page_url":"http://export.arxiv.org/pdf/1505.07293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Computer Vision and Pattern Recognition","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1505.07293","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1505.07293","pdf_url":"https://arxiv.org/pdf/1505.07293","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.6000000238418579}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W360623563","https://openalex.org/W1903029394","https://openalex.org/W2963881378","https://openalex.org/W2194775991","https://openalex.org/W1745334888","https://openalex.org/W3138715326","https://openalex.org/W2911016673","https://openalex.org/W2340897893","https://openalex.org/W2022508996","https://openalex.org/W1905829557","https://openalex.org/W1901129140","https://openalex.org/W1677182931","https://openalex.org/W2587989515","https://openalex.org/W2904466083","https://openalex.org/W3024859318","https://openalex.org/W2105340328","https://openalex.org/W3097800045","https://openalex.org/W3100159496","https://openalex.org/W2911605501","https://openalex.org/W2747668150"],"abstract_inverted_index":{"We":[0,199],"propose":[1],"a":[2,25,38,73,79,86,137],"novel":[3],"deep":[4,119,141],"architecture,":[5],"SegNet,":[6],"for":[7,43,127,130],"semantic":[8],"pixel":[9,44,63,131,197],"wise":[10,132],"image":[11,108,196],"labelling.":[12,133],"SegNet":[13,69,185,204,223],"has":[14],"several":[15],"attractive":[16],"properties;":[17],"(i)":[18],"it":[19,51],"only":[20],"requires":[21],"forward":[22],"evaluation":[23],"of":[24,58,72,75,101,117,170,203,230],"fully":[26],"learnt":[27],"function":[28],"to":[29,54,105,139,145,150,154,175,191,195],"obtain":[30],"smooth":[31],"label":[32,64],"predictions,":[33],"(ii)":[34],"with":[35,240],"increasing":[36],"depth,":[37,235],"larger":[39],"context":[40],"is":[41,52,70],"considered":[42],"labelling":[45],"which":[46,83,122],"improves":[47],"accuracy,":[48],"and":[49,165,180,212],"(iii)":[50],"easy":[53],"visualise":[55],"the":[56,62,99,102,168,201,216],"effect":[57],"feature":[59,96,110,143],"activation(s)":[60],"in":[61,162,173],"space":[65],"at":[66,98],"any":[67],"depth.":[68],"composed":[71],"stack":[74,82,104],"encoders":[76],"followed":[77],"by":[78,158,189],"corresponding":[80],"decoder":[81],"feeds":[84],"into":[85],"soft-max":[87],"classification":[88],"layer.":[89],"The":[90],"decoders":[91],"help":[92],"map":[93,140,192],"low":[94],"resolution":[95],"maps":[97,144],"output":[100],"encoder":[103,193],"full":[106],"input":[107,146],"size":[109],"maps.":[111],"This":[112,160],"addresses":[113],"an":[114],"important":[115],"drawback":[116],"recent":[118],"learning":[120,190],"approaches":[121],"have":[123],"adopted":[124],"networks":[125],"designed":[126],"object":[128],"categorization":[129],"These":[134],"methods":[135,153],"lack":[136],"mechanism":[138],"layer":[142],"dimensions.":[147],"They":[148],"resort":[149],"ad":[151],"hoc":[152],"upsample":[155],"features,":[156],"e.g.":[157],"replication.":[159],"results":[161,220],"noisy":[163],"predictions":[164],"also":[166],"restricts":[167],"number":[169],"pooling":[171],"layers":[172],"order":[174],"avoid":[176],"too":[177],"much":[178],"upsampling":[179],"thus":[181],"reduces":[182],"spatial":[183],"context.":[184],"overcomes":[186],"these":[187],"problems":[188],"outputs":[194],"labels.":[198],"test":[200],"performance":[202,226],"on":[205],"outdoor":[206],"RGB":[207],"scenes":[208,214],"from":[209,215],"CamVid,":[210],"KITTI":[211],"indoor":[213],"NYU":[217],"dataset.":[218],"Our":[219],"show":[221],"that":[222],"achieves":[224],"state-of-the-art":[225],"even":[227],"without":[228],"use":[229],"additional":[231],"cues":[232],"such":[233],"as":[234],"video":[236],"frames":[237],"or":[238],"post-processing":[239],"CRF":[241],"models.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":36},{"year":2022,"cited_by_count":36},{"year":2021,"cited_by_count":38},{"year":2020,"cited_by_count":41},{"year":2019,"cited_by_count":38},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":20},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2022-10-01T00:00:00"}