{"id":"https://openalex.org/W7213396339","doi":"https://doi.org/10.48550/arxiv.2609.16486","title":"VPRef: A Cross-Domain Benchmark for Referring Remote Sensing Image Segmentation","display_name":"VPRef: A Cross-Domain Benchmark for Referring Remote Sensing Image Segmentation","publication_year":2026,"publication_date":"2026-09-15","ids":{"openalex":"https://openalex.org/W7213396339","doi":"https://doi.org/10.48550/arxiv.2609.16486"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.16486","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.16486","pdf_url":"https://arxiv.org/pdf/2609.16486","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.16486","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005905993","display_name":"Quanwei Liu","orcid":"https://orcid.org/0000-0003-4976-1858","observed_orcids":["https://orcid.org/0000-0003-4976-1858"]},"institutions":[{"id":"https://openalex.org/I86467917","display_name":"James Cook University","ror":"https://ror.org/04gsp2c11","country_code":"AU","type":"education","lineage":["https://openalex.org/I86467917"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Liu, Quanwei","raw_affiliation_strings":["College of Science and Engineering , James Cook University , Cairns , 4878 , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Science and Engineering , James Cook University , Cairns , 4878 , Australia","institution_ids":["https://openalex.org/I86467917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151915436","display_name":"Tao Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86467917","display_name":"James Cook University","ror":"https://ror.org/04gsp2c11","country_code":"AU","type":"education","lineage":["https://openalex.org/I86467917"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Huang, Tao","raw_affiliation_strings":["College of Science and Engineering , James Cook University , Cairns , 4878 , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Science and Engineering , James Cook University , Cairns , 4878 , Australia","institution_ids":["https://openalex.org/I86467917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151878838","display_name":"Jiaqi Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86467917","display_name":"James Cook University","ror":"https://ror.org/04gsp2c11","country_code":"AU","type":"education","lineage":["https://openalex.org/I86467917"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yang, Jiaqi","raw_affiliation_strings":["College of Science and Engineering , James Cook University , Cairns , 4878 , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Science and Engineering , James Cook University , Cairns , 4878 , Australia","institution_ids":["https://openalex.org/I86467917"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127003905","display_name":"Wei Xiang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.5659000277519226,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.5659000277519226,"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":0.15770000219345093,"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":0.12489999830722809,"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/spectral-variability","display_name":"spectral variability","score":0.6290000081062317},{"id":"https://openalex.org/keywords/segment-anything-model","display_name":"Segment Anything Model","score":0.7160000205039978},{"id":"https://openalex.org/keywords/lora","display_name":"LoRa","score":0.6869999766349792},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7860000133514404},{"id":"https://openalex.org/keywords/earth-observation","display_name":"Earth observation","score":0.46799999475479126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7050999999046326},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6861000061035156},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5630000233650208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49070000648498535},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4661000072956085},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4507000148296356},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4262999892234802},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.42500001192092896},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.40070000290870667},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3546000123023987},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34790000319480896},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29910001158714294},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2872999906539917},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.2831999957561493},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.26420000195503235},{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C60777511","wikidata":"https://www.wikidata.org/wiki/Q3045002","display_name":"Concept drift","level":3,"score":0.2563000023365021},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C2778584072","wikidata":"https://www.wikidata.org/wiki/Q7353545","display_name":"Robustification","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.16486","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.16486","pdf_url":"https://arxiv.org/pdf/2609.16486","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.16486","doi":"https://doi.org/10.48550/arxiv.2609.16486","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.16486","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.16486","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.16486","pdf_url":"https://arxiv.org/pdf/2609.16486","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213396339.pdf","grobid_xml":"https://content.openalex.org/works/W7213396339.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W3206476077","https://openalex.org/W4403444411","https://openalex.org/W4415328489","https://openalex.org/W4417095222","https://openalex.org/W7164998532"],"related_works":["https://openalex.org/W7163704787","https://openalex.org/W7166733274","https://openalex.org/W4407570530","https://openalex.org/W7172527135","https://openalex.org/W7213875022","https://openalex.org/W4415707595","https://openalex.org/W7130706229","https://openalex.org/W4411019933","https://openalex.org/W7117366894","https://openalex.org/W4390629203"],"abstract_inverted_index":{"Rapid":[0],"advancements":[1],"in":[2],"vision-language":[3],"models":[4],"have":[5],"propelled":[6],"Referring":[7,65],"Remote":[8],"Sensing":[9],"Image":[10],"Segmentation":[11],"(RRSIS)":[12],"to":[13],"the":[14,56,63,92,122,161,174],"forefront":[15],"of":[16,124,173],"Earth":[17],"observation.":[18],"However,":[19],"practical":[20],"deployments":[21],"suffer":[22],"severe":[23],"performance":[24],"degradation":[25],"under":[26],"a":[27,74,84,131,179],"coupled":[28],"dual-drift":[29],"paradigm:":[30],"visual":[31,104,139],"domain":[32,87,140,187],"drift":[33,43,114],"from":[34,44],"cross-spatial-resolution":[35],"mismatches":[36],"and":[37,110,138,192],"spectral":[38],"variations,":[39],"alongside":[40],"textual":[41,112],"logic":[42,113],"unconstrained,":[45],"variable":[46],"user-input":[47],"granularities.":[48],"To":[49],"mitigate":[50],"these":[51],"bottlenecks,":[52],"this":[53,80],"paper":[54],"establishes":[55],"first":[57],"cross-domain":[58,166],"RRSIS":[59],"benchmark,":[60,81],"designated":[61],"as":[62],"Vaihingen-Potsdam":[64],"(VPRef)":[66],"dataset,":[67],"comprising":[68],"46,972":[69],"language-image-annotation":[70],"triplets":[71],"organized":[72],"into":[73],"three-tier":[75],"linguistic":[76,144],"hierarchy.":[77],"Building":[78],"upon":[79],"we":[82],"develop":[83],"tailored":[85],"parameter-efficient":[86],"adaptation":[88,188],"baseline":[89,181],"anchored":[90],"on":[91],"Segment":[93],"Anything":[94],"Model":[95],"(SAM3)":[96],"via":[97,115],"Low-Rank":[98],"Adaptation":[99],"(LoRA).":[100],"Our":[101],"framework":[102,163],"counteracts":[103],"distribution":[105,123],"discrepancies":[106],"through":[107],"pseudo-label-driven":[108],"self-training":[109],"addresses":[111],"random":[116],"multi-granularity":[117],"text":[118],"prompt":[119],"mixing.":[120],"Crucially,":[121],"empirical":[125],"metrics":[126],"across":[127],"ablative":[128],"variants":[129],"suggests":[130],"potential":[132],"decoupling":[133],"between":[134],"cross-modal":[135],"semantic":[136,148],"robustification":[137],"alignment,":[141],"demonstrating":[142],"that":[143],"variance":[145],"drives":[146],"fine-grained":[147],"invariance":[149],"while":[150,169],"pseudo-label":[151],"propagation":[152],"governs":[153],"macro-scale":[154],"spatial":[155],"grid":[156],"alignment.":[157],"Extensive":[158],"benchmarks":[159],"demonstrate":[160],"proposed":[162],"achieves":[164],"superior":[165],"segmentation":[167],"boundaries":[168],"modifying":[170],"merely":[171],"1.08\\%":[172],"foundational":[175],"parameter":[176],"footprint,":[177],"establishing":[178],"robust":[180],"for":[182],"future":[183],"multi-modal":[184],"remote":[185],"sensing":[186],"research.":[189],"The":[190],"dataset":[191],"code":[193],"will":[194],"be":[195],"available":[196],"at":[197],"https://github.com/quanweiliu/VPRef.":[198]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-17T00:00:00"}