{"id":"https://openalex.org/W7147253557","doi":"https://doi.org/10.48550/arxiv.2603.28603","title":"ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across Domains","display_name":"ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across Domains","publication_year":2026,"publication_date":"2026-03-30","ids":{"openalex":"https://openalex.org/W7147253557","doi":"https://doi.org/10.48550/arxiv.2603.28603"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.28603","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28603","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.28603","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076056185","display_name":"Pavel \u0160uma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suma, Pavel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086670028","display_name":"Giorgos Kordopatis-Zilos","orcid":"https://orcid.org/0000-0003-2297-4802"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kordopatis-Zilos, Giorgos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042126127","display_name":"Yannis Kalantidis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kalantidis, Yannis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132573853","display_name":"Giorgos Tolias","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tolias, Giorgos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.36640000343322754,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.36640000343322754,"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":0.2816999852657318,"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":0.21480000019073486,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.7662000060081482},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6646999716758728},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6504999995231628},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6179999709129333},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5945000052452087},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5703999996185303},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5059999823570251},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.4309000074863434}],"concepts":[{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7662000060081482},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6646999716758728},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6504999995231628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6496999859809875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6327000260353088},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6179999709129333},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5945000052452087},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5703999996185303},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5059999823570251},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.4309000074863434},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41670000553131104},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2919999957084656},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.28603","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28603","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":"doi:10.48550/arxiv.2603.28603","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28603","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":"article"},"sustainable_development_goals":[{"score":0.42860090732574463,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"instance-level":[1],"training":[2],"data":[3,27],"is":[4],"scarce,":[5],"so":[6],"models":[7],"are":[8],"typically":[9],"trained":[10],"on":[11,143],"domain-specific":[12],"datasets.":[13],"Yet":[14],"in":[15,48,139],"real-world":[16],"retrieval,":[17],"they":[18],"must":[19],"handle":[20],"diverse":[21],"domains,":[22],"making":[23],"generalization":[24],"to":[25,39],"unseen":[26,40],"critical.":[28],"We":[29],"introduce":[30],"ELViS,":[31],"an":[32,67,87],"image-to-image":[33],"similarity":[34,49],"model":[35,46],"that":[36,74,130],"generalizes":[37],"effectively":[38],"domains.":[41],"Unlike":[42],"conventional":[43],"approaches,":[44],"our":[45],"operates":[47],"space":[50],"rather":[51],"than":[52],"representation":[53],"space,":[54],"promoting":[55],"cross-domain":[56],"transfer.":[57],"It":[58],"leverages":[59],"local":[60],"descriptor":[61],"correspondences,":[62],"refines":[63],"their":[64,151],"similarities":[65],"through":[66],"optimal":[68],"transport":[69],"step":[70],"with":[71],"data-dependent":[72],"gains":[73],"suppress":[75],"uninformative":[76],"descriptors,":[77],"and":[78,100,117,120,142],"aggregates":[79],"strong":[80,93],"correspondences":[81],"via":[82],"a":[83,97,108,124,136,148],"voting":[84],"process":[85],"into":[86],"image-level":[88],"similarity.":[89],"This":[90],"design":[91],"injects":[92],"inductive":[94],"biases,":[95],"yielding":[96],"simple,":[98],"efficient,":[99],"interpretable":[101],"model.":[102],"To":[103],"assess":[104],"generalization,":[105],"we":[106],"compile":[107],"benchmark":[109],"of":[110,150],"eight":[111],"datasets":[112],"spanning":[113],"landmarks,":[114],"artworks,":[115],"products,":[116],"multi-domain":[118],"collections,":[119],"evaluate":[121],"ELViS":[122,131],"as":[123],"re-ranking":[125],"method.":[126],"Our":[127],"experiments":[128],"show":[129],"outperforms":[132],"competing":[133],"methods":[134],"by":[135],"large":[137],"margin":[138],"out-of-domain":[140],"scenarios":[141],"average,":[144],"while":[145],"requiring":[146],"only":[147],"fraction":[149],"computational":[152],"cost.":[153],"Code":[154],"available":[155],"at:":[156],"https://github.com/pavelsuma/ELViS/":[157]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-02T00:00:00"}