{"id":"https://openalex.org/W3015045658","doi":null,"title":"Long-tail learning with attributes","display_name":"Long-tail learning with attributes","publication_year":2020,"publication_date":"2020-04-05","ids":{"openalex":"https://openalex.org/W3015045658","mag":"3015045658"},"language":"en","primary_location":{"id":"mag:3015045658","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2004.02235","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.02235","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029218807","display_name":"Dvir Samuel","orcid":"https://orcid.org/0000-0003-3573-2220","observed_orcids":["https://orcid.org/0000-0003-3573-2220"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dvir Samuel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080909499","display_name":"Yuval Atzmon","orcid":"https://orcid.org/0000-0003-3817-3698","observed_orcids":["https://orcid.org/0000-0003-3817-3698"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuval Atzmon","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3817-3698","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5045719865","display_name":"Gal Chechik","orcid":"https://orcid.org/0000-0001-9164-5303","observed_orcids":["https://orcid.org/0000-0001-9164-5303"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gal Chechik","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9164-5303","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":1,"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":0.9818999767303467,"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":0.9818999767303467,"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":0.011099999770522118,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.0010000000474974513,"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/class-imbalance","display_name":"class imbalance","score":0.7480000257492065},{"id":"https://openalex.org/keywords/few-shot-learning","display_name":"few-shot learning","score":0.8199999928474426},{"id":"https://openalex.org/keywords/semantic-features","display_name":"semantic features","score":0.9259999990463257},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.8450000286102295},{"id":"https://openalex.org/keywords/familiarity-bias","display_name":"familiarity bias","score":0.9860000014305115},{"id":"https://openalex.org/keywords/forecast-calibration","display_name":"forecast calibration","score":0.5860000252723694},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.6470000147819519}],"concepts":[{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.7926303148269653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7210873365402222},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6950403451919556},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6746758222579956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6201416254043579},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5201273560523987},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.49432849884033203},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37706321477890015},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08023494482040405},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3015045658","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2004.02235","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3015045658","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2004.02235","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1618905105","https://openalex.org/W1797268635","https://openalex.org/W2035782089","https://openalex.org/W2070148066","https://openalex.org/W2118978333","https://openalex.org/W2194775991","https://openalex.org/W2400717490","https://openalex.org/W2552383788","https://openalex.org/W2596142952","https://openalex.org/W2603705233","https://openalex.org/W2753300133","https://openalex.org/W2753880617","https://openalex.org/W2767106145","https://openalex.org/W2772366472","https://openalex.org/W2799215068","https://openalex.org/W2887567284","https://openalex.org/W2899746634","https://openalex.org/W2924476266","https://openalex.org/W2935725472","https://openalex.org/W2950276680","https://openalex.org/W2962689421","https://openalex.org/W2963351448","https://openalex.org/W2963499153","https://openalex.org/W2963880109","https://openalex.org/W2963960318","https://openalex.org/W2964105864","https://openalex.org/W2964121744","https://openalex.org/W2964162033","https://openalex.org/W2969186079","https://openalex.org/W2981188200","https://openalex.org/W3009441615","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W3038539952","https://openalex.org/W3120940860","https://openalex.org/W4312885504","https://openalex.org/W4402168684","https://openalex.org/W4401878832","https://openalex.org/W4405402436","https://openalex.org/W7160890311","https://openalex.org/W4313151233","https://openalex.org/W4399506362","https://openalex.org/W4404486676"],"abstract_inverted_index":{"Learning":[0],"to":[1,15,26,31,46,85,106,155],"classify":[2,56],"images":[3],"with":[4,150],"unbalanced":[5,65,116],"class":[6],"distributions":[7],"is":[8,13,44,119],"challenged\nby":[9],"two":[10],"effects:":[11],"It":[12],"hard":[14,25,84],"learn":[16],"tail":[17,41,134],"classes":[18],"that":[19,130],"have":[20],"few":[21],"samples,":[22],"and":[23,34,55,93,109,136,152,163],"it\nis":[24],"adapt":[27],"a":[28,68,124,127,137],"single":[29],"model":[30],"both":[32],"richly-sampled":[33],"poorly-sampled\nclasses.":[35],"To":[36],"address":[37,107],"few-shot":[38],"learning":[39,104,161],"of":[40,52,79,115],"classes,":[42,135],"it":[43,83,154],"useful":[45],"fuse\nadditional":[47],"information":[48,112],"in":[49,113,173],"the":[50,133,145],"form":[51],"semantic":[53],"attributes":[54,151,166],"based":[57,120],"on\nmulti-modal":[58],"information.":[59],"Unfortunately,":[60],"as":[61],"we":[62,96],"show":[63],"below,":[64],"data":[66],"leads\nto":[67],"familiarity":[69],"bias,":[70],"where":[71],"classifiers":[72],"favor":[73],"sample-rich":[74],"classes.":[75],"This":[76],"bias\nand":[77],"lack":[78],"calibrated":[80],"predictions":[81],"make":[82],"fuse":[86,110],"correctly":[87],"information\nfrom":[88],"multiple":[89],"modalities":[90],"like":[91],"vision":[92,125],"attributes.":[94],"Here":[95],"describe":[97],"DRAGON,":[98],"a\nnovel":[99],"modular":[100],"architecture":[101],"for":[102,148,176],"long-tail":[103,160],"designed":[105],"these\nbiases":[108],"multi-modal":[111],"face":[114],"data.":[117],"Our\narchitecture":[118],"on":[121,132],"three":[122],"classifiers:":[123],"expert,":[126],"semantic\nattribute":[128],"expert":[129],"excels":[131],"debias-and-fuse":[138],"module\nto":[139],"combine":[140],"their":[141],"predictions.":[142],"We":[143],"present":[144],"first":[146],"benchmark":[147],"long-tail\nlearning":[149],"use":[153],"evaluate":[156],"DRAGON.":[157],"DRAGON":[158,169],"outperforms\nstate-of-the-art":[159],"models":[162],"Generalized":[164],"Few-Shot-Learning\nwith":[165],"(GFSL-a)":[167],"models.":[168],"also":[170],"obtains":[171],"SoTA":[172],"some":[174],"existing\nbenchmarks":[175],"single-modality":[177],"GFSL.":[178]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2020-04-10T00:00:00"}