{"id":"https://openalex.org/W7130428497","doi":"https://doi.org/10.1109/tcsvt.2026.3665905","title":"The Teacher\u2013Student Interactive Cycle: Joint Optimization With Inner-Loop Self-Distillation in Prompted Foundation Models for Efficient Semantic Segmentation","display_name":"The Teacher\u2013Student Interactive Cycle: Joint Optimization With Inner-Loop Self-Distillation in Prompted Foundation Models for Efficient Semantic Segmentation","publication_year":2026,"publication_date":"2026-02-18","ids":{"openalex":"https://openalex.org/W7130428497","doi":"https://doi.org/10.1109/tcsvt.2026.3665905"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3665905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3665905","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","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":null,"display_name":"Meng Li","orcid":"https://orcid.org/0009-0009-3630-6208"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Li","raw_affiliation_strings":["Department of Electronics and Information Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-3630-6208","affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126304942","display_name":"Qi Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Zhao","raw_affiliation_strings":["Department of Electronics and Information Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3508-027X","affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029244560","display_name":"Shuchang Lyu","orcid":"https://orcid.org/0000-0001-9769-7083"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuchang Lyu","raw_affiliation_strings":["Department of Electronics and Information Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9769-7083","affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126286427","display_name":"Jun Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Jiang","raw_affiliation_strings":["Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0004-6099-5844","affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121936943","display_name":"Longhao Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longhao Zou","raw_affiliation_strings":["Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102802382","display_name":"Dingding Yao","orcid":"https://orcid.org/0000-0002-9610-8782"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dingding Yao","raw_affiliation_strings":["Institute of Acoustics Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9610-8782","affiliations":[{"raw_affiliation_string":"Institute of Acoustics Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126343436","display_name":"Guangliang Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guangliang Cheng","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Liverpool, U.K"],"raw_orcid":"https://orcid.org/0000-0001-8686-9513","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Liverpool, U.K","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126316540","display_name":"Chenguang Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chenguang Yang","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Liverpool, U.K"],"raw_orcid":"https://orcid.org/0000-0001-5255-5559","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Liverpool, U.K","institution_ids":["https://openalex.org/I146655781"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20549189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"7","first_page":"10763","last_page":"10779"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9492999911308289,"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":0.9492999911308289,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.015599999576807022,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.006200000178068876,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/pascal","display_name":"Pascal (unit)","score":0.683899998664856},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6065999865531921},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4652999937534332},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4372999966144562},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4196000099182129},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.4142000079154968},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4124999940395355},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.40400001406669617},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.38670000433921814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8579999804496765},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.683899998664856},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6065999865531921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.583899974822998},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5594000220298767},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.40400001406669617},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30379998683929443},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.2858000099658966},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.25060001015663147},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3665905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3665905","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7122112512588501,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2724800082","display_name":null,"funder_award_id":"2025ZD1303100","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G4285606817","display_name":null,"funder_award_id":"501QYJC2025102002","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"the":[1,6,103,160,163,207],"field":[2],"of":[3,10,209],"semantic":[4,50,108,129],"segmentation,":[5],"high":[7],"computational":[8],"cost":[9],"deep":[11],"models":[12,39],"poses":[13],"a":[14,31,89,117,134,139,144],"major":[15],"barrier":[16],"to":[17,40,101,147,158,212],"deployment":[18],"on":[19,61,183,195],"edge":[20],"devices.":[21],"Among":[22],"various":[23],"efficiency-oriented":[24],"methods,":[25,214],"knowledge":[26,36,45],"distillation":[27,46],"has":[28],"emerged":[29],"as":[30,143],"promising":[32],"technique":[33],"for":[34,48,96,107],"transferring":[35],"from":[37],"large":[38,62],"lightweight":[41,135],"networks.":[42],"However,":[43],"current":[44],"methods":[47],"efficient":[49,128],"segmentation":[51,218],"still":[52],"face":[53],"two":[54,113],"key":[55],"challenges:":[56],"(1)":[57],"they":[58,74],"often":[59,99],"rely":[60],"offline":[63,184],"pre-trained":[64,185],"teacher":[65,164],"networks":[66],"that":[67,79],"remain":[68],"fixed":[69],"during":[70],"training,":[71],"and":[72,171,187,204],"(2)":[73],"lack":[75],"joint":[76,178],"optimization":[77,180],"mechanisms":[78],"enable":[80],"effective":[81,189],"teacher-student":[82],"interaction":[83],"in":[84,220],"pixel-wise":[85],"dense":[86],"prediction.":[87],"As":[88],"result,":[90],"mutual":[91],"learning":[92],"strategies":[93],"originally":[94],"designed":[95],"image-level":[97],"classification":[98],"fail":[100],"capture":[102],"fine-grained":[104,166],"consistency":[105],"required":[106],"segmentation.":[109,130],"To":[110],"address":[111],"these":[112],"challenges,":[114],"we":[115],"propose":[116],"novel":[118],"training":[119],"framework":[120],"termed":[121],"Teacher-Student":[122],"Interactive":[123],"Cycle":[124],"(TSIC),":[125],"which":[126],"performs":[127],"Specifically,":[131],"TSIC":[132,215],"integrates":[133],"student":[136,153],"network":[137],"into":[138],"prompt-based":[140],"foundation":[141],"model":[142],"prompted":[145],"segmentor":[146],"assist":[148],"an":[149],"online-trained":[150],"teacher.":[151],"The":[152],"provides":[154],"coarse":[155],"mask":[156],"prompts":[157],"guide":[159],"teacher,":[161],"while":[162],"offers":[165],"supervision":[167],"through":[168],"posterior":[169],"probabilities":[170],"intermediate":[172],"feature":[173],"maps.":[174],"This":[175],"loop":[176],"enables":[177],"online":[179],"without":[181],"relying":[182],"teachers":[186],"fosters":[188],"bidirectional":[190],"communication.":[191],"Extensive":[192],"experiments":[193],"conducted":[194],"several":[196],"benchmark":[197],"datasets,":[198],"including":[199],"Cityscapes,":[200],"Pascal":[201],"VOC,":[202],"CamVid,":[203],"ADE20k,":[205],"demonstrate":[206],"effectiveness":[208],"TSIC.":[210],"Compared":[211],"previous":[213],"achieves":[216],"superior":[217],"mIoU":[219],"most":[221],"scenarios.":[222],"Our":[223],"code":[224],"will":[225],"be":[226],"made":[227],"publicly":[228],"available":[229],"at":[230],"https://github.com/CV-ShuchangLyu/TSIC.":[231]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-02-19T00:00:00"}