{"id":"https://openalex.org/W2899901372","doi":"https://doi.org/10.1137/18m1167267","title":"Revisiting Deep Structured Models for Pixel-Level Labeling with Gradient-Based Inference","display_name":"Revisiting Deep Structured Models for Pixel-Level Labeling with Gradient-Based Inference","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2899901372","doi":"https://doi.org/10.1137/18m1167267","mag":"2899901372"},"language":"en","primary_location":{"id":"doi:10.1137/18m1167267","is_oa":false,"landing_page_url":"https://doi.org/10.1137/18m1167267","pdf_url":null,"source":{"id":"https://openalex.org/S152600803","display_name":"SIAM Journal on Imaging Sciences","issn_l":"1936-4954","issn":["1936-4954"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Imaging Sciences","raw_type":"journal-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/A5101961337","display_name":"M\u00e5ns Larsson","orcid":"https://orcid.org/0000-0003-3137-1405"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"M\u00e5ns Larsson","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035108037","display_name":"Anurag Arnab","orcid":"https://orcid.org/0000-0002-5216-4838"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anurag Arnab","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100726973","display_name":"Shuai Zheng","orcid":"https://orcid.org/0000-0002-1636-631X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Zheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042899882","display_name":"Philip H. S. Torr","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philip Torr","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112556001","display_name":"Fredrik Kahl","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fredrik Kahl","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101961337"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.425,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68446611,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"11","issue":"4","first_page":"2610","last_page":"2628"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994000196456909,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980000257492065,"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/conditional-random-field","display_name":"Conditional random field","score":0.8299530744552612},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.720266580581665},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6932379007339478},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5962609648704529},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5747831463813782},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5568700432777405},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5561615824699402},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.525375485420227},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5109300017356873},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5001611709594727},{"id":"https://openalex.org/keywords/random-field","display_name":"Random field","score":0.475643128156662},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.44251909852027893},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44077789783477783},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.42597153782844543},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37832877039909363},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2937379479408264},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.11272439360618591},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09199923276901245}],"concepts":[{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.8299530744552612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.720266580581665},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6932379007339478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5962609648704529},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5747831463813782},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5568700432777405},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5561615824699402},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.525375485420227},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5109300017356873},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5001611709594727},{"id":"https://openalex.org/C130402806","wikidata":"https://www.wikidata.org/wiki/Q5361768","display_name":"Random field","level":2,"score":0.475643128156662},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.44251909852027893},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44077789783477783},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.42597153782844543},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37832877039909363},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2937379479408264},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.11272439360618591},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09199923276901245},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1137/18m1167267","is_oa":false,"landing_page_url":"https://doi.org/10.1137/18m1167267","pdf_url":null,"source":{"id":"https://openalex.org/S152600803","display_name":"SIAM Journal on Imaging Sciences","issn_l":"1936-4954","issn":["1936-4954"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Imaging Sciences","raw_type":"journal-article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:07172dfd-e81e-435c-a810-1b193de2734d","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:07172dfd-e81e-435c-a810-1b193de2734d","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal article"},{"id":"pmh:oai:research.chalmers.se:507715","is_oa":false,"landing_page_url":"https://research.chalmers.se/en/publication/507715","pdf_url":null,"source":{"id":"https://openalex.org/S4306402469","display_name":"Chalmers Research (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:research.chalmers.se:509889","is_oa":false,"landing_page_url":"https://research.chalmers.se/en/publication/48f0669e-07b4-423b-a37e-5047a504b926","pdf_url":null,"source":{"id":"https://openalex.org/S4306402469","display_name":"Chalmers Research (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1203979484","display_name":null,"funder_award_id":"EP/N019474/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G1277543710","display_name":null,"funder_award_id":"EP/M013774/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G1882191505","display_name":null,"funder_award_id":"2017-01942","funder_id":"https://openalex.org/F4320321030","funder_display_name":"VINNOVA"},{"id":"https://openalex.org/G2028311846","display_name":null,"funder_award_id":"ERC-2012-Adg 321162-HELIOS","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"},{"id":"https://openalex.org/G482967556","display_name":null,"funder_award_id":"MURI EP/N019474/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8287411776","display_name":null,"funder_award_id":"2016-04445","funder_id":"https://openalex.org/F4320321033","funder_display_name":"Svenska Forskningsr\u00e5det Formas"},{"id":"https://openalex.org/G8416736120","display_name":null,"funder_award_id":"Seebibyte EP/M013774/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320940","display_name":"Stiftelsen f\u00f6r\u00a0Strategisk Forskning","ror":"https://ror.org/044wr7g58"},{"id":"https://openalex.org/F4320321030","display_name":"VINNOVA","ror":"https://ror.org/01kd5m353"},{"id":"https://openalex.org/F4320321033","display_name":"Svenska Forskningsr\u00e5det Formas","ror":"https://ror.org/03pjs1y45"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1964772475","https://openalex.org/W2016384870","https://openalex.org/W2031489346","https://openalex.org/W2037227137","https://openalex.org/W2074078071","https://openalex.org/W2124351162","https://openalex.org/W2167219413","https://openalex.org/W2395611524","https://openalex.org/W2412782625","https://openalex.org/W2784226479"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W2093471820","https://openalex.org/W4386190339","https://openalex.org/W2968424575","https://openalex.org/W50079190","https://openalex.org/W2114846443","https://openalex.org/W3142333283","https://openalex.org/W2963336968","https://openalex.org/W2805329439","https://openalex.org/W2293372754"],"abstract_inverted_index":{"Semantic":[0],"segmentation":[1,131,156],"and":[2,38,41,68,84,133],"other":[3],"pixel-level":[4],"labeling":[5],"tasks":[6],"have":[7],"made":[8],"significant":[9],"progress":[10],"recently":[11],"due":[12],"to":[13,34,113,161],"the":[14,104],"deep":[15],"learning":[16,69],"paradigm.":[17],"Many":[18],"state-of-the-art":[19,163],"structured":[20],"prediction":[21],"methods":[22],"also":[23],"include":[24],"a":[25,30,65,94,143],"random":[26,46,77],"field":[27,47,78],"model":[28,35],"with":[29,49,157],"hand-crafted":[31],"Gaussian":[32],"potential":[33,98],"spatial":[36,83,117],"priors":[37],"label":[39],"consistencies":[40],"feature-based":[42],"image":[43,50],"conditioning.":[44],"These":[45],"models":[48],"conditioning":[51],"typically":[52],"require":[53],"computationally":[54],"demanding":[55],"filtering":[56],"techniques":[57],"during":[58],"inference.":[59],"In":[60,90],"this":[61],"paper,":[62],"we":[63,92],"present":[64],"new":[66,95],"inference":[67],"framework":[70,147],"which":[71,100],"can":[72,129],"learn":[73],"arbitrary":[74],"pairwise":[75],"conditional":[76],"(CRF)":[79],"potentials.":[80],"Both":[81],"standard":[82],"high-dimensional":[85],"bilateral":[86,105],"kernels":[87],"are":[88,119,138],"considered.":[89],"addition,":[91],"introduce":[93],"type":[96],"of":[97,110],"function":[99],"is":[101,122,148],"image-dependent":[102],"like":[103],"kernel,":[106],"but":[107],"an":[108],"order":[109],"magnitude":[111],"faster":[112],"compute":[114],"since":[115],"only":[116],"convolutions":[118],"employed.":[120],"It":[121],"empirically":[123],"demonstrated":[124],"that":[125,134],"such":[126],"learned":[127],"potentials":[128],"improve":[130],"accuracy":[132],"certain":[135],"label-class":[136],"interactions":[137],"indeed":[139],"better":[140],"modeled":[141],"by":[142],"non-Gaussian":[144],"potential.":[145],"Our":[146],"evaluated":[149],"on":[150],"several":[151],"public":[152],"benchmarks":[153],"for":[154],"semantic":[155],"improved":[158],"performance":[159],"compared":[160],"previous":[162],"CNN+CRF":[164],"models.":[165]},"counts_by_year":[{"year":2019,"cited_by_count":4}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}