{"id":"https://openalex.org/W4224933351","doi":"https://doi.org/10.1109/icassp43922.2022.9747568","title":"Visual Representation Learning with Self-Supervised Attention for Low-Label High-Data Regime","display_name":"Visual Representation Learning with Self-Supervised Attention for Low-Label High-Data Regime","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224933351","doi":"https://doi.org/10.1109/icassp43922.2022.9747568"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747568","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5057923827","display_name":"Prarthana Bhattacharyya","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Prarthana Bhattacharyya","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066785489","display_name":"Chenge Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenge Li","raw_affiliation_strings":["Amazon Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039479036","display_name":"Xiaonan Zhao","orcid":"https://orcid.org/0000-0003-2003-6177"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaonan Zhao","raw_affiliation_strings":["Amazon Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060014350","display_name":"Istv\u00e1n Feh\u00e9rv\u00e1ri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Istvan Fehervari","raw_affiliation_strings":["Amazon Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049887375","display_name":"Jason Sun","orcid":"https://orcid.org/0000-0002-0499-4263"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jason Sun","raw_affiliation_strings":["Amazon Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5004,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.60992314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3453","last_page":"3457"},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9642000198364258,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.837054967880249},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6572279930114746},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5658636689186096},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5435601472854614},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.460070937871933},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.45126864314079285},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42191094160079956},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4190014898777008},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4161509573459625},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4136263430118561},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3790452480316162},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3588376045227051},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.15544945001602173}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.837054967880249},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6572279930114746},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5658636689186096},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5435601472854614},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.460070937871933},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.45126864314079285},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42191094160079956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4190014898777008},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4161509573459625},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4136263430118561},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3790452480316162},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3588376045227051},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15544945001602173},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747568","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2138011018","https://openalex.org/W2601450892","https://openalex.org/W2604763608","https://openalex.org/W2605102252","https://openalex.org/W2689134854","https://openalex.org/W2742093937","https://openalex.org/W2753160622","https://openalex.org/W2894906112","https://openalex.org/W2963026686","https://openalex.org/W2963350250","https://openalex.org/W2964271799","https://openalex.org/W2994633389","https://openalex.org/W3005680577","https://openalex.org/W3009561768","https://openalex.org/W3035524453","https://openalex.org/W3094502228","https://openalex.org/W3096805028","https://openalex.org/W3099486271","https://openalex.org/W3109083691","https://openalex.org/W3109684201","https://openalex.org/W3122520870","https://openalex.org/W3159481202","https://openalex.org/W3161622534","https://openalex.org/W3188008942","https://openalex.org/W4289241454","https://openalex.org/W4300860215","https://openalex.org/W6600609147","https://openalex.org/W6735236233","https://openalex.org/W6736057607","https://openalex.org/W6742288159","https://openalex.org/W6743661861","https://openalex.org/W6764716228","https://openalex.org/W6767151586","https://openalex.org/W6774314701","https://openalex.org/W6774670964","https://openalex.org/W6780975210","https://openalex.org/W6784333009","https://openalex.org/W6788840927"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2942366970","https://openalex.org/W2807634898","https://openalex.org/W1692008701","https://openalex.org/W2597588799","https://openalex.org/W4360593462","https://openalex.org/W2894446834"],"abstract_inverted_index":{"Self-supervision":[0],"has":[1],"shown":[2],"outstanding":[3],"results":[4],"for":[5,12,158,165,179],"natural":[6],"language":[7],"processing,":[8],"and":[9,18,26,67,87,91,108,139,163,172,177],"more":[10],"recently,":[11],"image":[13,65,69,97,126,167,181],"recognition.":[14],"Simultaneously,":[15],"vision":[16,34,47,57],"transformers":[17,48],"its":[19],"variants":[20],"have":[21],"emerged":[22],"as":[23],"a":[24,84,133],"promising":[25],"scalable":[27],"alternative":[28],"to":[29,43,53,74,82,88,113,116],"convolutions":[30],"on":[31,105,132,154],"various":[32],"computer":[33,56],"tasks.":[35],"In":[36],"this":[37,110],"paper,":[38],"we":[39,99,128],"are":[40],"the":[41,60,76,152],"first":[42],"question":[44],"if":[45],"self-supervised":[46,148],"(SSL-ViTs)":[49],"can":[50],"be":[51],"adapted":[52],"two":[54],"important":[55],"tasks":[58],"in":[59],"low-label,":[61],"high-data":[62],"regime:":[63],"few-shot":[64,96,166],"classification":[66,98,168],"zero-shot":[68,125,180],"retrieval.":[70],"The":[71],"motivation":[72],"is":[73,187],"reduce":[75],"number":[77,121],"of":[78,122],"manual":[79],"annotations":[80],"required":[81],"train":[83,100],"visual":[85],"embedder,":[86],"produce":[89],"generalizable":[90],"semantically":[92],"meaningful":[93],"embeddings.":[94],"For":[95,124],"SSL-ViTs":[101,130],"without":[102,136],"any":[103,137],"supervision,":[104],"external":[106],"data,":[107],"use":[109,129],"trained":[111],"embedder":[112],"adapt":[114],"quickly":[115],"novel":[117],"classes":[118],"with":[119,142],"limited":[120],"labels.":[123],"retrieval,":[127],"pre-trained":[131],"large":[134],"dataset":[135],"labels":[138],"fine-tune":[140],"them":[141],"several":[143,155],"metric":[144],"learning":[145],"objectives.":[146],"Our":[147],"attention":[149],"representations":[150],"outperforms":[151],"state-of-the-art":[153],"public":[156],"benchmarks":[157],"both":[159],"tasks,":[160],"namely":[161],"miniImageNet":[162],"CUB200":[164,178],"by":[169,183],"up-to":[170,184],"6%-10%,":[171],"Stanford":[173],"Online":[174],"Products,":[175],"Cars196":[176],"retrieval":[182],"4%-11%.":[185],"Code":[186],"available":[188],"at":[189],"https://github.com/AutoVision-cloud/SSL-ViT-lowlabel-highdata.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}