{"id":"https://openalex.org/W7084064162","doi":"https://doi.org/10.1109/tcsvt.2025.3616588","title":"CLIP-to-Seg Distillation for Zero-Shot Semantic Segmentation","display_name":"CLIP-to-Seg Distillation for Zero-Shot Semantic Segmentation","publication_year":2025,"publication_date":"2025-10-01","ids":{"openalex":"https://openalex.org/W7084064162","doi":"https://doi.org/10.1109/tcsvt.2025.3616588"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3616588","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3616588","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tcsvt.2025.3616588","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jialei Chen","orcid":"https://orcid.org/0009-0005-0654-4281"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jialei Chen","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0009-0005-0654-4281","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhenzhen Quan","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenzhen Quan","raw_affiliation_strings":["School of Information Science and Engineering, Shandong University, Qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenkai Zhang","orcid":"https://orcid.org/0000-0002-7258-272X"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chenkai Zhang","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7258-272X","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xu Zheng","orcid":"https://orcid.org/0000-0003-4008-8951"},"institutions":[{"id":"https://openalex.org/I4210164767","display_name":"GCI Science & Technology (China)","ror":"https://ror.org/05tj2eg80","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210164767"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Xu Zheng","raw_affiliation_strings":["AI Thrust, The Hong Kong University of Science and Technology, Guangzhou Campus (HKUST-GZ), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4008-8951","affiliations":[{"raw_affiliation_string":"AI Thrust, The Hong Kong University of Science and Technology, Guangzhou Campus (HKUST-GZ), Guangzhou, China","institution_ids":["https://openalex.org/I4210164767","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Daisuke Deguchi","orcid":"https://orcid.org/0000-0003-0603-8790"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Deguchi","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0003-0603-8790","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":null,"display_name":"Hiroshi Murase","orcid":"https://orcid.org/0000-0002-8103-9294"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Murase","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0002-8103-9294","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.7191,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.9578193,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"36","issue":"3","first_page":"3665","last_page":"3678"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12223","display_name":"Leptospirosis research and findings","score":0.9602000117301941,"subfield":{"id":"https://openalex.org/subfields/2405","display_name":"Parasitology"},"field":{"id":"https://openalex.org/fields/24","display_name":"Immunology and Microbiology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12223","display_name":"Leptospirosis research and findings","score":0.9602000117301941,"subfield":{"id":"https://openalex.org/subfields/2405","display_name":"Parasitology"},"field":{"id":"https://openalex.org/fields/24","display_name":"Immunology and Microbiology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11086","display_name":"Parasitic Infections and Diagnostics","score":0.0017000000225380063,"subfield":{"id":"https://openalex.org/subfields/2405","display_name":"Parasitology"},"field":{"id":"https://openalex.org/fields/24","display_name":"Immunology and Microbiology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12232","display_name":"Yersinia bacterium, plague, ectoparasites research","score":0.001500000013038516,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.8320000171661377},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5920000076293945},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5896000266075134},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5679000020027161},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5590000152587891},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.5242000222206116},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.4519999921321869}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8320000171661377},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8043000102043152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6008999943733215},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5920000076293945},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5896000266075134},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5679000020027161},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5590000152587891},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.5242000222206116},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4740000069141388},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.4519999921321869},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.38510000705718994},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2930999994277954},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3616588","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3616588","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1109/tcsvt.2025.3616588","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3616588","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4527619183063507}],"awards":[{"id":"https://openalex.org/G1898306257","display_name":"\u4eba\u7269\u884c\u52d5\u3092\u624b\u639b\u304b\u308a\u3068\u3057\u305f\u8eca\u8f09\u6620\u50cf\u30af\u30e9\u30a6\u30c9\u63a2\u7d22\u306b\u3088\u308b\u77e5\u8b58\u7372\u5f97\u578b\u8a8d\u8b58\u57fa\u76e4\u306e\u69cb\u7bc9","funder_award_id":"23K28164","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G1973904818","display_name":null,"funder_award_id":"23K28164","funder_id":"https://openalex.org/F4320322622","funder_display_name":"Toyota Motor Corporation"},{"id":"https://openalex.org/G3711620445","display_name":null,"funder_award_id":"JPMJCR22D1","funder_id":"https://openalex.org/F4320322622","funder_display_name":"Toyota Motor Corporation"},{"id":"https://openalex.org/G4826095242","display_name":"\u6559\u80b2\u5927\u822a\u6d77\u6642\u4ee3\u306e\u7f85\u91dd\u76e4\uff1a\u5b66\u7fd2\u5206\u6790\u306e\u4fe1\u983c\u57fa\u76e4ReLAX\u306e\u5275\u51fa","funder_award_id":"JPMJCR22D1","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"},{"id":"https://openalex.org/G8079321836","display_name":"Scene Understanding and Knowledge Extension by Active Open-world Recognition","funder_award_id":"24H00733","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320322622","display_name":"Toyota Motor Corporation","ror":"https://ror.org/02zqm6r10"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1903029394","https://openalex.org/W2037227137","https://openalex.org/W2125215748","https://openalex.org/W2194775991","https://openalex.org/W2412782625","https://openalex.org/W2561196672","https://openalex.org/W2601564443","https://openalex.org/W2787091153","https://openalex.org/W2798991696","https://openalex.org/W2924485953","https://openalex.org/W2963351448","https://openalex.org/W2982242214","https://openalex.org/W3049293589","https://openalex.org/W3110290422","https://openalex.org/W3170841864","https://openalex.org/W3201755784","https://openalex.org/W3202461785","https://openalex.org/W3202473909","https://openalex.org/W4312458986","https://openalex.org/W4312651322","https://openalex.org/W4312815172","https://openalex.org/W4312890493","https://openalex.org/W4312912313","https://openalex.org/W4312935996","https://openalex.org/W4312960937","https://openalex.org/W4313139298","https://openalex.org/W4323891852","https://openalex.org/W4386065874","https://openalex.org/W4386075819","https://openalex.org/W4386075822","https://openalex.org/W4386075882","https://openalex.org/W4386076289","https://openalex.org/W4386076397","https://openalex.org/W4390871743","https://openalex.org/W4390872930","https://openalex.org/W4390873603","https://openalex.org/W4390874575","https://openalex.org/W4391547487","https://openalex.org/W4391697061","https://openalex.org/W4392796515","https://openalex.org/W4393029495","https://openalex.org/W4402702914","https://openalex.org/W4402710294","https://openalex.org/W4402716047","https://openalex.org/W4402733565","https://openalex.org/W4402961794","https://openalex.org/W4403843568","https://openalex.org/W4403929887","https://openalex.org/W4404446909","https://openalex.org/W4404627538","https://openalex.org/W4404722477","https://openalex.org/W4405632022","https://openalex.org/W4405934235","https://openalex.org/W4406946980","https://openalex.org/W7133220737"],"related_works":[],"abstract_inverted_index":{"CLIP":[0,18,39,173],"has":[1],"greatly":[2],"advanced":[3],"zero-shot":[4,74,191],"segmentation":[5,20,37,80,89,97,129,154,187],"by":[6,117,141],"leveraging":[7],"its":[8],"strong":[9,157],"visual-language":[10],"association":[11],"and":[12,30,38,50,66,91,146,165,189],"generalization":[13,75,158],"capability.":[14],"However,":[15],"directly":[16],"adapting":[17],"for":[19,120,136,160],"often":[21,41],"yields":[22],"suboptimal":[23],"results":[24],"due":[25],"to":[26,43,69,77,87,95,109],"inconsistencies":[27],"between":[28],"image":[29],"pixel-level":[31],"prediction":[32,111],"objectives.":[33],"Additionally,":[34],"merely":[35],"combining":[36],"models":[40,155,188],"leads":[42],"disjoint":[44],"optimization,":[45],"introducing":[46,176],"significant":[47],"computational":[48],"overhead":[49],"additional":[51],"parameters.":[52],"To":[53,124],"address":[54],"these":[55],"issues,":[56],"we":[57,131],"propose":[58],"a":[59],"novel":[60],"CLIP-to-Seg":[61,167],"Distillation":[62],"approach,":[63],"incorporating":[64],"global":[65],"local":[67,106],"distillation":[68,83,103],"flexibly":[70],"transfer":[71],"CLIP\u2019s":[72,105],"powerful":[73],"capability":[76],"existing":[78,152,185],"closed-set":[79,153,186],"models.":[81],"Global":[82],"leverages":[84],"CLS":[85],"tokens":[86],"condense":[88],"features":[90],"distills":[92],"high-level":[93],"concepts":[94,162],"the":[96,127,137,172],"model":[98,174],"via":[99],"image-level":[100],"features.":[101,148],"Local":[102],"adapts":[104],"semantic":[107],"transferability":[108],"dense":[110,147],"tasks":[112],"using":[113],"object-level":[114],"features,":[115],"aided":[116],"pseudo-mask":[118],"generation":[119],"latent":[121,133,139],"class":[122],"mining.":[123],"further":[125],"generalize":[126],"CLIP-distilled":[128],"model,":[130],"generate":[132],"text":[134,144],"embeddings":[135,145],"mined":[138],"classes":[140],"coordinating":[142],"their":[143],"Our":[149],"method":[150,181],"equips":[151],"with":[156],"capabilities":[159],"open":[161],"through":[163],"effective":[164],"flexible":[166],"distillation.":[168],"Without":[169],"relying":[170],"on":[171,196],"or":[175],"extra":[177],"inference":[178],"overhead,":[179],"our":[180],"seamlessly":[182],"integrates":[183],"into":[184],"enables":[190],"capability,":[192],"achieving":[193],"state-of-the-art":[194],"performance":[195],"multiple":[197],"benchmarks.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}
