{"id":"https://openalex.org/W4379806244","doi":"https://doi.org/10.1145/3591106.3592266","title":"Improving Image Encoders for General-Purpose Nearest Neighbor Search and Classification","display_name":"Improving Image Encoders for General-Purpose Nearest Neighbor Search and Classification","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4379806244","doi":"https://doi.org/10.1145/3591106.3592266"},"language":"en","primary_location":{"id":"doi:10.1145/3591106.3592266","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002095484","display_name":"Konstantin Schall","orcid":"https://orcid.org/0000-0003-3548-0537"},"institutions":[{"id":"https://openalex.org/I122228004","display_name":"HTW Berlin - University of Applied Sciences","ror":"https://ror.org/01xzwj424","country_code":"DE","type":"education","lineage":["https://openalex.org/I122228004"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Konstantin Schall","raw_affiliation_strings":["HTW Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3548-0537","affiliations":[{"raw_affiliation_string":"HTW Berlin, Germany","institution_ids":["https://openalex.org/I122228004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048382625","display_name":"Kai Uwe Barthel","orcid":"https://orcid.org/0000-0001-6309-572X"},"institutions":[{"id":"https://openalex.org/I122228004","display_name":"HTW Berlin - University of Applied Sciences","ror":"https://ror.org/01xzwj424","country_code":"DE","type":"education","lineage":["https://openalex.org/I122228004"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kai Uwe Barthel","raw_affiliation_strings":["HTW Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6309-572X","affiliations":[{"raw_affiliation_string":"HTW Berlin, Germany","institution_ids":["https://openalex.org/I122228004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073245734","display_name":"Nico Hezel","orcid":"https://orcid.org/0000-0002-3957-4672"},"institutions":[{"id":"https://openalex.org/I122228004","display_name":"HTW Berlin - University of Applied Sciences","ror":"https://ror.org/01xzwj424","country_code":"DE","type":"education","lineage":["https://openalex.org/I122228004"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nico Hezel","raw_affiliation_strings":["HTW Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3957-4672","affiliations":[{"raw_affiliation_string":"HTW Berlin, Germany","institution_ids":["https://openalex.org/I122228004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088022579","display_name":"Klaus Jung","orcid":"https://orcid.org/0000-0002-3600-6848"},"institutions":[{"id":"https://openalex.org/I122228004","display_name":"HTW Berlin - University of Applied Sciences","ror":"https://ror.org/01xzwj424","country_code":"DE","type":"education","lineage":["https://openalex.org/I122228004"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus Jung","raw_affiliation_strings":["HTW Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3600-6848","affiliations":[{"raw_affiliation_string":"HTW Berlin, Germany","institution_ids":["https://openalex.org/I122228004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002095484"],"corresponding_institution_ids":["https://openalex.org/I122228004"],"apc_list":null,"apc_paid":null,"fwci":0.7065,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71446843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"66"},"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.7980733513832092},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.7127463221549988},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6442664265632629},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.6292632818222046},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6164547204971313},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5923239588737488},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5916746258735657},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5867332816123962},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5421541333198547},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5306671261787415},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5152397751808167},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49721387028694153},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.4356818199157715},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4335528314113617},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10078907012939453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7980733513832092},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.7127463221549988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6442664265632629},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.6292632818222046},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6164547204971313},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5923239588737488},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5916746258735657},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5867332816123962},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5421541333198547},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5306671261787415},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5152397751808167},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49721387028694153},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.4356818199157715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4335528314113617},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10078907012939453},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3591106.3592266","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W204268067","https://openalex.org/W1583837637","https://openalex.org/W1965804146","https://openalex.org/W2040002737","https://openalex.org/W2117539524","https://openalex.org/W2138011018","https://openalex.org/W2141362318","https://openalex.org/W2151103935","https://openalex.org/W2185175083","https://openalex.org/W2340690086","https://openalex.org/W2533598788","https://openalex.org/W2560674852","https://openalex.org/W2797977484","https://openalex.org/W2903950532","https://openalex.org/W2953937638","https://openalex.org/W2961301154","https://openalex.org/W2963026686","https://openalex.org/W2963588253","https://openalex.org/W2969985801","https://openalex.org/W2980282514","https://openalex.org/W3008526508","https://openalex.org/W3035305184","https://openalex.org/W3036224891","https://openalex.org/W3081372396","https://openalex.org/W3097217077","https://openalex.org/W3110536152","https://openalex.org/W3202202633","https://openalex.org/W3216047630","https://openalex.org/W4286986508","https://openalex.org/W4287203292","https://openalex.org/W4287823094","https://openalex.org/W4306798676","https://openalex.org/W4306820534","https://openalex.org/W4309137644","https://openalex.org/W4312956471","https://openalex.org/W4313136445","https://openalex.org/W4313156423","https://openalex.org/W4313484649","https://openalex.org/W6702248584","https://openalex.org/W6839260653","https://openalex.org/W6931259419"],"related_works":["https://openalex.org/W2148008870","https://openalex.org/W2381195555","https://openalex.org/W4246757943","https://openalex.org/W2368606575","https://openalex.org/W2132753198","https://openalex.org/W2369874856","https://openalex.org/W2182477562","https://openalex.org/W2792185758","https://openalex.org/W2787484455","https://openalex.org/W2119808169"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,25,37,81,114],"computer":[3],"vision":[4,9,47,70,124],"research":[5],"led":[6],"to":[7,14],"large":[8,108],"foundation":[10,48],"models":[11,49,86,143],"that":[12,95,121],"generalize":[13],"a":[15,92,105,127],"broad":[16],"range":[17],"of":[18,45,68,84,107,130],"image":[19,27,145],"domains":[20],"and":[21,59,72,99,136],"perform":[22],"exceptionally":[23],"well":[24],"various":[26,69],"based":[28],"tasks.":[29],"However,":[30],"content-based":[31],"image-to-image":[32],"retrieval":[33,58,98],"is":[34,76],"often":[35],"overlooked":[36],"this":[38],"context.":[39],"This":[40],"paper":[41],"investigates":[42],"the":[43,66,82,122],"effectiveness":[44],"different":[46,133],"on":[50],"two":[51],"challenging":[52],"nearest":[53],"neighbor":[54],"search-based":[55,134],"tasks:":[56],"zero-shot":[57,97],"k-NN":[60,100],"classification.":[61],"A":[62],"benchmark":[63],"for":[64,144],"evaluating":[65],"performance":[67,83],"encoders":[71,125],"their":[73],"pre-training":[74],"methods":[75],"established,":[77],"where":[78],"significant":[79],"differences":[80],"these":[85],"are":[87],"observed.":[88],"Additionally,":[89],"we":[90],"propose":[91],"fine-tuning":[93],"regime":[94],"improves":[96],"classification":[101],"through":[102],"training":[103],"with":[104],"combination":[106],"publicly":[109],"available":[110],"datasets":[111],"without":[112],"specializing":[113],"any":[115],"data":[116],"domain.":[117],"Our":[118],"results":[119],"show":[120],"retrained":[123],"have":[126],"higher":[128],"degree":[129],"generalization":[131],"across":[132],"tasks":[135],"can":[137],"be":[138],"used":[139],"as":[140],"general-purpose":[141],"embedding":[142],"retrieval.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}