{"id":"https://openalex.org/W7128383512","doi":"https://doi.org/10.1093/comjnl/bxaf135","title":"AKSeg: combining variable kernel convolution with Nash multi task learning","display_name":"AKSeg: combining variable kernel convolution with Nash multi task learning","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W7128383512","doi":"https://doi.org/10.1093/comjnl/bxaf135"},"language":"en","primary_location":{"id":"doi:10.1093/comjnl/bxaf135","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxaf135","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","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/A5045471237","display_name":"Wei Xie","orcid":"https://orcid.org/0009-0008-0633-178X"},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xie","raw_affiliation_strings":["China Electronics Technology Group Corporation No. 10 Institute , No. 48 Yingkang Road, Jinniu District, Chengdu 610036 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Electronics Technology Group Corporation No. 10 Institute , No. 48 Yingkang Road, Jinniu District, Chengdu 610036 ,","institution_ids":["https://openalex.org/I2800372957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125395831","display_name":"Keyu Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keyu Shen","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University , No. 999 Xi'an Road, Pidu District, Chengdu 611756 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University , No. 999 Xi'an Road, Pidu District, Chengdu 611756 ,","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125397007","display_name":"Zhenxing Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I3017770710","display_name":"China North Industries Group Corporation (China)","ror":"https://ror.org/00cwdhv97","country_code":"CN","type":"company","lineage":["https://openalex.org/I3017770710"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenxing Yang","raw_affiliation_strings":["China North Chemical Research and Design Institute, China North Industries Group Corporation Limited , No. 55 Zizhuyuan Road, Haidian District, Beijing 100089 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China North Chemical Research and Design Institute, China North Industries Group Corporation Limited , No. 55 Zizhuyuan Road, Haidian District, Beijing 100089 ,","institution_ids":["https://openalex.org/I3017770710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090143892","display_name":"Yutao Liu","orcid":"https://orcid.org/0009-0001-2001-7876"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutao Liu","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University , No. 999 Xi'an Road, Pidu District, Chengdu 611756 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University , No. 999 Xi'an Road, Pidu District, Chengdu 611756 ,","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100430876","display_name":"Xi Zhang","orcid":"https://orcid.org/0000-0003-3415-5345"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobo Zhang","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University , No. 999 Xi'an Road, Pidu District, Chengdu 611756 ,","State Key Laboratory of Bridge Intelligent and Green Construction, Southwest Jiaotong University , No. 999 Xi'an Road, Pidu District, Chengdu 611756 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University , No. 999 Xi'an Road, Pidu District, Chengdu 611756 ,","institution_ids":["https://openalex.org/I4800084"]},{"raw_affiliation_string":"State Key Laboratory of Bridge Intelligent and Green Construction, Southwest Jiaotong University , No. 999 Xi'an Road, Pidu District, Chengdu 611756 ,","institution_ids":["https://openalex.org/I4800084","https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2635,"currency":"GBP","value_usd":3232},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8079047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"69","issue":"4","first_page":"644","last_page":"654"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.2533999979496002,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.2533999979496002,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.14409999549388885,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.052799999713897705,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6071000099182129},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5748000144958496},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5302000045776367},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4821999967098236},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4609000086784363},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4287000000476837},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41339999437332153},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.40700000524520874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.753000020980835},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6071000099182129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.588699996471405},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5748000144958496},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5302000045776367},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4821999967098236},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4609000086784363},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41339999437332153},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.40700000524520874},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3950999975204468},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3443000018596649},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27959999442100525},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.26269999146461487}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/comjnl/bxaf135","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxaf135","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2845541968","https://openalex.org/W3206824631","https://openalex.org/W4288424521","https://openalex.org/W4400859202"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"In":[1],"complex":[2],"image":[3,209],"multi-task":[4,55,68,132,210],"learning,":[5],"the":[6,59,63,77,81,86,111,150,163,176,185,203],"precision":[7],"and":[8,25,88,116,130,194],"effectiveness":[9],"of":[10,80,90,98,152,165,205],"feature":[11,28,125],"extraction":[12,126],"are":[13],"often":[14],"constrained":[15],"by":[16,158,188,192,198],"traditional":[17],"convolutional":[18,91],"methods,":[19],"including":[20],"issues":[21],"with":[22,52],"scale":[23],"invariance":[24],"difficulties":[26],"in":[27,110,207],"sharing":[29],"across":[30,127],"tasks.":[31],"To":[32,121],"tackle":[33,122],"these":[34],"challenges,":[35],"we":[36],"introduce":[37],"a":[38,53,104],"straightforward":[39],"but":[40],"efficient":[41],"model":[42],"called":[43],"AKSeg.":[44],"AKSeg":[45,73,93,112,135,148,177,183,206],"effectively":[46],"combines":[47],"Adaptive":[48],"Kernel":[49],"Convolution":[50],"(AKConv)":[51],"Nash-based":[54],"learning":[56,133,211],"strategy":[57,107],"within":[58],"SegNet":[60],"framework,":[61],"improving":[62],"model\u2019s":[64],"ability":[65],"to":[66,113,139],"capture":[67,96],"features":[69,97,143],"from":[70,101],"images.":[71,102],"First,":[72],"incorporates":[74],"AKConv":[75],"into":[76],"encoder":[78],"layer":[79],"SegNet.":[82],"By":[83],"dynamically":[84],"adjusting":[85],"size":[87],"shape":[89],"kernels,":[92],"can":[94],"accurately":[95],"various":[99],"scales":[100],"Then,":[103],"Nash":[105],"game":[106],"is":[108],"employed":[109],"update":[114],"parameters":[115],"weights":[117],"as":[118],"tasks":[119,129],"change.":[120],"challenges":[123],"like":[124],"varying":[128],"improve":[131],"capability,":[134],"utilizes":[136],"multiple":[137],"channels":[138],"efficiently":[140],"extract":[141],"distinct":[142],"for":[144],"each":[145],"task.":[146],"Additionally,":[147],"addresses":[149],"issue":[151],"dead":[153],"Rectified":[154,167],"Linear":[155,168],"Unit":[156,169],"(ReLU)":[157],"eliminating":[159],"inactive":[160],"neurons":[161],"through":[162],"use":[164],"Leaky":[166],"(LeakyReLU).":[170],"Extensive":[171],"experimental":[172],"results":[173,201],"demonstrate":[174],"that":[175],"outperforms":[178],"baseline":[179],"methods":[180],"remarkably.":[181],"Specifically,":[182],"reduces":[184],"loss":[186],"value":[187],"4.48%,":[189],"improves":[190],"mIoU":[191],"4.52%,":[193],"increases":[195],"pixel":[196],"accuracy":[197],"1.73%.":[199],"These":[200],"validate":[202],"usefulness":[204],"enhancing":[208],"performance.":[212]},"counts_by_year":[],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2026-02-10T00:00:00"}