{"id":"https://openalex.org/W4400222282","doi":"https://doi.org/10.48550/arxiv.2406.19400","title":"Deep Convolutional Neural Networks Meet Variational Shape Compactness\n Priors for Image Segmentation","display_name":"Deep Convolutional Neural Networks Meet Variational Shape Compactness\n Priors for Image Segmentation","publication_year":2024,"publication_date":"2024-05-23","ids":{"openalex":"https://openalex.org/W4400222282","doi":"https://doi.org/10.48550/arxiv.2406.19400"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.19400","pdf_url":"http://arxiv.org/pdf/2406.19400","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"posted-content","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/2406.19400","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079911869","display_name":"Kehui Zhang","orcid":"https://orcid.org/0000-0002-1358-1196"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Kehui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100774099","display_name":"Lingfeng Li","orcid":"https://orcid.org/0000-0002-4698-4100"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Lingfeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458897","display_name":"Hao Liu","orcid":"https://orcid.org/0000-0003-4271-1567"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Hao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076360956","display_name":"Jing Yuan","orcid":"https://orcid.org/0000-0001-9325-4891"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Jing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101951979","display_name":"Xue\u2013Cheng Tai","orcid":"https://orcid.org/0000-0003-3359-9104"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tai, Xue-Cheng","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":84},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.7507,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.7507,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7907108},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7766117},{"id":"https://openalex.org/C18648836","wikidata":"https://www.wikidata.org/wiki/Q381892","display_name":"Compact space","level":2,"score":0.70654213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6921041},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.66592526},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5567218},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.519348},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.50853026},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4619027},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42177022},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28289795},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.078629434},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.075377375}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.19400","pdf_url":"http://arxiv.org/pdf/2406.19400","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.19400","pdf_url":"http://arxiv.org/pdf/2406.19400","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4387315838","https://openalex.org/W4386190339","https://openalex.org/W4252969132","https://openalex.org/W2805799113","https://openalex.org/W2580650124","https://openalex.org/W2402800040","https://openalex.org/W2121543990","https://openalex.org/W2000020320","https://openalex.org/W1981078319","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Shape":[0],"compactness":[1,173],"is":[2],"a":[3,33,40,50,66,78,191],"key":[4],"geometrical":[5],"property":[6],"to":[7,24,56,103,128,137,160],"describe":[8],"interesting":[9],"regions":[10,131],"in":[11,48,152],"many":[12],"image":[13,28,133,194],"segmentation":[14,29,134],"tasks.":[15],"In":[16,179],"this":[17],"paper,":[18],"we":[19,64,89],"propose":[20,65,95],"two":[21],"novel":[22,67,97],"algorithms":[23,37,148,151,183],"solve":[25],"the":[26,54,58,91,109,113,116,146,161,181],"introduced":[27],"problem":[30,41],"that":[31,145],"incorporates":[32],"shape-compactness":[34],"prior.":[35],"Existing":[36],"for":[38],"such":[39],"often":[42],"suffer":[43],"from":[44],"computational":[45],"inefficiency,":[46],"difficulty":[47],"reaching":[49],"local":[51],"minimum,":[52],"and":[53,76,94,155,166,172],"need":[55],"fine-tune":[57],"hyperparameters.":[59],"To":[60],"address":[61],"these":[62],"issues,":[63],"optimization":[68,80],"model":[69,75],"along":[70],"with":[71,168],"its":[72],"equivalent":[73],"primal-dual":[74,84,98],"introduce":[77],"new":[79],"algorithm":[81,101,119],"based":[82],"on":[83,108,175,190],"threshold":[85],"dynamics":[86],"(PD-TD).":[87],"Additionally,":[88],"relax":[90],"solution":[92],"constraint":[93],"another":[96],"soft":[99],"threshold-dynamics":[100],"(PD-STD)":[102],"achieve":[104],"superior":[105],"performance.":[106],"Based":[107],"variational":[110],"explanation":[111],"of":[112,164],"sigmoid":[114],"layer,":[115],"proposed":[117,147,182],"PD-STD":[118],"can":[120],"be":[121],"integrated":[122],"into":[123],"Deep":[124],"Neural":[125],"Networks":[126],"(DNNs)":[127],"enforce":[129],"compact":[130],"as":[132],"results.":[135],"Compared":[136],"existing":[138],"deep":[139],"learning":[140],"methods,":[141],"extensive":[142],"experiments":[143],"demonstrated":[144],"outperformed":[149],"state-of-the-art":[150],"numerical":[153],"efficiency":[154],"effectiveness,":[156],"especially":[157],"while":[158],"applying":[159],"popular":[162],"networks":[163],"DeepLabV3":[165],"IrisParseNet":[167],"higher":[169],"IoU,":[170],"dice,":[171],"metrics":[174],"noisy":[176,193],"Iris":[177],"datasets.":[178],"particular,":[180],"significantly":[184],"improve":[185],"IoU":[186],"by":[187],"20%":[188],"training":[189],"highly":[192],"dataset.":[195]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4400222282","counts_by_year":[],"updated_date":"2024-12-29T11:27:23.130896","created_date":"2024-07-02"}