{"id":"https://openalex.org/W7165732187","doi":"https://doi.org/10.48550/arxiv.2606.24297","title":"Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matching","display_name":"Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matching","publication_year":2026,"publication_date":"2026-06-23","ids":{"openalex":"https://openalex.org/W7165732187","doi":"https://doi.org/10.48550/arxiv.2606.24297"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.24297","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.24297","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.24297","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100802179","display_name":"Sujun Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Sujun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102968758","display_name":"Mingwu Ren","orcid":"https://orcid.org/0000-0001-5576-3281"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Mingwu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139238125","display_name":"Haofeng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Haofeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"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":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.7713000178337097,"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":0.7713000178337097,"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":0.14059999585151672,"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":0.023000000044703484,"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":0.6053000092506409},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.602400004863739},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5516999959945679},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5159000158309937},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.504800021648407},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49399998784065247},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.48339998722076416},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4690999984741211},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.41370001435279846}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8203999996185303},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6053000092506409},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.602400004863739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5871000289916992},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5516999959945679},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5159000158309937},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.504800021648407},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49399998784065247},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.48339998722076416},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4690999984741211},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46219998598098755},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.3327000141143799},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3133000135421753},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.2761000096797943},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2759999930858612},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26919999718666077},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.24297","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.24297","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.24297","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.24297","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6833603382110596}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Cross-domain":[0],"Few-shot":[1],"Segmentation":[2],"(CD-FSS)":[3],"aims":[4],"to":[5,12,74,88,164,166],"transfer":[6],"knowledge":[7],"learned":[8],"from":[9,161],"source":[10],"domain":[11,177],"distinct":[13],"target":[14,18,176],"domains,":[15],"segmenting":[16],"unseen":[17],"classes":[19],"with":[20,128],"only":[21,67],"a":[22,85],"few":[23],"annotated":[24],"samples.":[25],"Although":[26],"existing":[27],"methods":[28],"have":[29],"made":[30],"significant":[31],"progress,":[32],"they":[33],"still":[34],"rely":[35],"on":[36,174],"training":[37,91],"or":[38,70],"fine-tuning":[39],"processes,":[40],"which":[41],"incur":[42],"high":[43],"computational":[44],"costs":[45],"and":[46,54,83,93,119,144],"risk":[47],"overfitting.":[48,75,94],"We":[49],"observe":[50],"that":[51,122,180],"when":[52],"powerful":[53],"general-purpose":[55],"vision":[56,99],"foundation":[57],"models":[58],"are":[59],"incorporated":[60],"into":[61],"these":[62],"methods,":[63],"their":[64],"performance":[65,185],"shows":[66],"marginal":[68],"improvement":[69],"even":[71],"degrades":[72],"due":[73],"To":[76],"address":[77],"this,":[78],"we":[79],"eliminate":[80],"trainable":[81],"parameters":[82],"propose":[84],"training-free":[86],"framework":[87,103],"avoid":[89],"both":[90],"overhead":[92],"Built":[95],"upon":[96],"the":[97,112,133,152],"self-supervised":[98],"encoder":[100],"DINOv3,":[101],"our":[102,181],"addresses":[104],"cross-domain":[105],"challenges":[106],"through":[107,146],"three":[108],"core":[109],"modules.":[110],"First,":[111],"Semantic-aware":[113],"Feature":[114],"Re-fusion":[115],"(SAFR)":[116],"module":[117,138,157],"identifies":[118],"re-fuses":[120],"features":[121],"emphasize":[123],"semantic":[124,130,140,168],"patterns,":[125],"generating":[126],"representations":[127],"enhanced":[129],"discriminability.":[131],"Additionally,":[132],"Adaptive":[134],"Support":[135],"Enhancement":[136],"(ASE)":[137],"narrows":[139],"gaps":[141],"between":[142],"support":[143],"query":[145,148],"robust":[147],"information":[149],"aggregation.":[150],"Finally,":[151],"Hybrid":[153],"Prototype":[154],"Matching":[155],"(HPM)":[156],"integrates":[158],"matching":[159],"results":[160],"diverse":[162],"prototypes":[163],"adapt":[165],"varying":[167],"complexity":[169],"across":[170],"domains.":[171],"Extensive":[172],"experiments":[173],"four":[175],"datasets":[178],"demonstrate":[179],"method":[182],"achieves":[183],"state-of-the-art":[184],"in":[186],"CD-FSS":[187],"without":[188],"any":[189],"training.":[190]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-25T00:00:00"}