{"id":"https://openalex.org/W4389469751","doi":"https://doi.org/10.48550/arxiv.2312.02205","title":"Disentangling the Effects of Data Augmentation and Format Transform in Self-Supervised Learning of Image Representations","display_name":"Disentangling the Effects of Data Augmentation and Format Transform in Self-Supervised Learning of Image Representations","publication_year":2023,"publication_date":"2023-12-02","ids":{"openalex":"https://openalex.org/W4389469751","doi":"https://doi.org/10.48550/arxiv.2312.02205"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2312.02205","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.02205","pdf_url":"https://arxiv.org/pdf/2312.02205","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/2312.02205","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047427141","display_name":"Neha Kalibhat","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kalibhat, Neha","raw_affiliation_strings":["University of Maryland , College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland , College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062812480","display_name":"Warren R. Morningstar","orcid":"https://orcid.org/0000-0002-5153-0920","observed_orcids":["https://orcid.org/0000-0002-5153-0920"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Morningstar, Warren","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039995184","display_name":"A. Bijamov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bijamov, Alex","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036831783","display_name":"Luyang Liu","orcid":"https://orcid.org/0000-0002-9002-3788","observed_orcids":["https://orcid.org/0000-0002-9002-3788"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Luyang","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027454515","display_name":"Karan Singhal","orcid":"https://orcid.org/0000-0001-9002-7490","observed_orcids":["https://orcid.org/0000-0001-9002-7490"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Singhal, Karan","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086361722","display_name":"P. Mansfield","orcid":"https://orcid.org/0000-0003-4969-0543","observed_orcids":["https://orcid.org/0000-0003-4969-0543"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mansfield, Philip","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"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":0.9872999787330627,"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":0.9872999787330627,"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":0.006099999882280827,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0008999999845400453,"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/self-supervised-learning","display_name":"self-supervised learning","score":0.9959999918937683},{"id":"https://openalex.org/keywords/image-representation-learning","display_name":"image representation learning","score":0.753000020980835},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.9639999866485596},{"id":"https://openalex.org/keywords/frequency-space","display_name":"frequency space","score":0.5220000147819519},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.5419999957084656},{"id":"https://openalex.org/keywords/few-shot-learning","display_name":"few-shot learning","score":0.9419999718666077},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.9210000038146973},{"id":"https://openalex.org/keywords/imagenet-1k","display_name":"ImageNet-1K","score":0.718999981880188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.789535403251648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5904773473739624},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5325974822044373},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.4819633662700653},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4449618458747864},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4408954381942749},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42368972301483154},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32328540086746216},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10245615243911743},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2312.02205","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.02205","pdf_url":"https://arxiv.org/pdf/2312.02205","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.2312.02205","doi":"https://doi.org/10.48550/arxiv.2312.02205","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.02205","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2312.02205","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.02205","pdf_url":"https://arxiv.org/pdf/2312.02205","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":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389469751.pdf","grobid_xml":"https://content.openalex.org/works/W4389469751.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4389363461","https://openalex.org/W4281556535","https://openalex.org/W4404352908","https://openalex.org/W4403318841","https://openalex.org/W4292829995","https://openalex.org/W4399695819","https://openalex.org/W4415797979","https://openalex.org/W4388514416","https://openalex.org/W4224918068","https://openalex.org/W4319453448"],"abstract_inverted_index":{"Self-Supervised":[0],"Learning":[1],"(SSL)":[2],"enables":[3],"training":[4,110],"performant":[5],"models":[6,112],"using":[7,146],"limited":[8],"labeled":[9],"data.":[10],"One":[11],"of":[12,21,24,84,116,159,168],"the":[13,19,25,62,66,71,82,123,157,166,169],"pillars":[14],"underlying":[15],"vision":[16,94],"SSL":[17,111,138],"is":[18],"use":[20],"data":[22],"augmentations/perturbations":[23],"input":[26],"which":[27],"do":[28,59],"not":[29,60],"significantly":[30],"alter":[31],"its":[32],"semantic":[33],"content.":[34],"For":[35],"audio":[36],"and":[37,87,91,107,118,142],"other":[38],"temporal":[39],"signals,":[40],"augmentations":[41,88,98,120],"are":[42],"commonly":[43],"used":[44],"alongside":[45],"format":[46,57,85,153],"transforms":[47,51,58,86,154],"such":[48],"as":[49],"Fourier":[50,103],"or":[52],"wavelet":[53],"transforms.":[54],"Unlike":[55],"augmentations,":[56],"change":[61],"information":[63,73],"contained":[64],"in":[65,74,99,140],"data;":[67],"rather,":[68],"they":[69],"express":[70],"same":[72],"different":[75],"coordinates.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80,149],"study":[81],"effects":[83],"both":[89],"separately":[90],"together":[92],"on":[93,113,131],"SSL.":[95],"We":[96,133],"define":[97],"frequency":[100],"space":[101],"called":[102],"Domain":[104],"Augmentations":[105],"(FDA)":[106],"show":[108,135],"that":[109,152],"a":[114],"combination":[115,167],"these":[117],"image":[119],"can":[121,155],"improve":[122,156],"downstream":[124],"classification":[125],"accuracy":[126],"by":[127],"up":[128],"to":[129],"1.3%":[130],"ImageNet-1K.":[132],"also":[134,150],"improvements":[136],"against":[137],"baselines":[139],"few-shot":[141],"transfer":[143],"learning":[144],"setups":[145],"FDA.":[147],"Surprisingly,":[148],"observe":[151],"quality":[158],"learned":[160],"representations":[161],"even":[162],"without":[163],"augmentations;":[164],"however,":[165],"two":[170],"techniques":[171],"yields":[172],"better":[173],"quality.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-12-08T00:00:00"}