{"id":"https://openalex.org/W4416407751","doi":"https://doi.org/10.1109/iccv51701.2025.01912","title":"Balancing Conservatism and Aggressiveness: Prototype-Affinity Hybrid Network for Few-Shot Segmentation","display_name":"Balancing Conservatism and Aggressiveness: Prototype-Affinity Hybrid Network for Few-Shot Segmentation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416407751","doi":"https://doi.org/10.1109/iccv51701.2025.01912"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.19140","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101590543","display_name":"Tianyu Zou","orcid":"https://orcid.org/0000-0002-5402-2796"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianyu Zou","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011707621","display_name":"Shengwu Xiong","orcid":"https://orcid.org/0000-0002-4006-7029"},"institutions":[{"id":"https://openalex.org/I4210100789","display_name":"Wuhan College","ror":"https://ror.org/01dashf18","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210100789"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengwu Xiong","raw_affiliation_strings":["Interdisciplinary Artificial Intelligence Research Institute, Wuhan College"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Artificial Intelligence Research Institute, Wuhan College","institution_ids":["https://openalex.org/I4210100789"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053695187","display_name":"Ruilin Yao","orcid":"https://orcid.org/0009-0002-6654-2294"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruilin Yao","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101967703","display_name":"Yi Rong","orcid":"https://orcid.org/0000-0003-4867-6811"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Rong","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101590543"],"corresponding_institution_ids":["https://openalex.org/I196699116"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3322496,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20561","last_page":"20571"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.48590001463890076,"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":0.48590001463890076,"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":0.44670000672340393,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.014499999582767487,"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/segmentation","display_name":"Segmentation","score":0.7354999780654907},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5591999888420105},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49320000410079956},{"id":"https://openalex.org/keywords/hybrid-learning","display_name":"Hybrid learning","score":0.4602000117301941},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.45010000467300415},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.43220001459121704},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.3889999985694885},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3792000114917755}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7354999780654907},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7315000295639038},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5591999888420105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5476999878883362},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5001000165939331},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49320000410079956},{"id":"https://openalex.org/C3018790387","wikidata":"https://www.wikidata.org/wiki/Q869010","display_name":"Hybrid learning","level":2,"score":0.4602000117301941},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.45010000467300415},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.43220001459121704},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.335999995470047},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.2768000066280365},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.19140","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.19140","pdf_url":"https://arxiv.org/pdf/2507.19140","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.19140","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.19140","pdf_url":null,"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":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.19140","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.19140","pdf_url":"https://arxiv.org/pdf/2507.19140","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4653825012","display_name":null,"funder_award_id":"62176194","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5747248502","display_name":null,"funder_award_id":"2023BAB083","funder_id":"https://openalex.org/F4320328876","funder_display_name":"Hebei Provincial Key Research Projects"},{"id":"https://openalex.org/G6356431383","display_name":null,"funder_award_id":"2022ZD0160604","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320328876","display_name":"Hebei Provincial Key Research Projects","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,63],"paper":[1],"studies":[2],"the":[3,42,69,86,130,144,155,166,169,179],"few-shot":[4],"segmentation":[5,87,180],"(FSS)":[6],"task,":[7],"which":[8,99],"aims":[9],"to":[10,14,59,67,84,142],"segment":[11],"objects":[12],"belonging":[13],"unseen":[15],"categories":[16],"in":[17,114,147],"a":[18,23,26,94,101,134],"query":[19,150],"image":[20,151],"by":[21,45,75,133],"learning":[22,47,56,121,137],"model":[24,122,138],"on":[25,201],"small":[27],"number":[28],"of":[29,35,54,79,118,168,182],"well-annotated":[30],"support":[31,148],"samples.":[32],"Our":[33],"analysis":[34],"two":[36,77,127],"mainstream":[37],"FSS":[38,80],"paradigms":[39],"reveals":[40],"that":[41,189],"predictions":[43,131],"made":[44],"prototype":[46,136,140],"methods":[48,57,195],"are":[49],"usually":[50],"conservative,":[51],"while":[52],"those":[53],"affinity":[55,120,124,170],"tend":[58],"be":[60,173],"more":[61],"aggressive.":[62],"observation":[64],"motivates":[65],"us":[66],"balance":[68],"conservative":[70],"and":[71,107,149,153,198,204,220],"aggressive":[72],"information":[73,146],"captured":[74],"these":[76],"types":[78],"frameworks":[81],"so":[82],"as":[83],"improve":[85],"performance.":[88],"To":[89],"achieve":[90],"this,":[91],"we":[92],"propose":[93],"**P**rototype-**A**ffinity":[95],"**H**ybrid":[96],"**Net**work":[97],"(PAHNet),":[98],"introduces":[100],"Prototype-guided":[102],"Feature":[103],"Enhancement":[104],"(PFE)":[105],"module":[106,113],"an":[108,119],"Attention":[109],"Score":[110],"Calibration":[111],"(ASC)":[112],"each":[115],"attention":[116],"block":[117],"(called":[123,139],"learner).":[125],"These":[126],"modules":[128],"utilize":[129],"generated":[132],"pre-trained":[135],"predictor)":[141],"enhance":[143],"foreground":[145],"representations":[152],"suppress":[154],"mismatched":[156],"foreground-background":[157],"(FG-BG)":[158],"relationships":[159],"between":[160],"them,":[161],"respectively.":[162],"In":[163],"this":[164],"way,":[165],"aggressiveness":[167],"learner":[171],"can":[172],"effectively":[174],"mitigated,":[175],"thereby":[176],"eventually":[177],"increasing":[178],"accuracy":[181],"our":[183],"PAHNet":[184,190],"method.":[185],"Experimental":[186],"results":[187],"show":[188],"outperforms":[191],"most":[192],"recently":[193],"proposed":[194],"across":[196],"1-shot":[197],"5-shot":[199],"settings":[200],"both":[202],"PASCAL-5$^i$":[203],"COCO-20$^i$":[205],"datasets,":[206],"suggesting":[207],"its":[208],"effectiveness.":[209],"The":[210],"code":[211],"is":[212],"available":[213],"at:":[214],"[GitHub":[215],"-":[216],"tianyu-zou/PAHNet:":[217],"Balancing":[218],"Conservatism":[219],"Aggressiveness:":[221],"Prototype-Affinity":[222],"Hybrid":[223],"Network":[224],"for":[225],"Few-Shot":[226],"Segmentation":[227],"(ICCV'25)](https://github.com/tianyu-zou/PAHNet)":[228]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}