{"id":"https://openalex.org/W7166573401","doi":"https://doi.org/10.48550/arxiv.2606.27864","title":"A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $\\mathrm{O}(2)$","display_name":"A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $\\mathrm{O}(2)$","publication_year":2026,"publication_date":"2026-06-26","ids":{"openalex":"https://openalex.org/W7166573401","doi":"https://doi.org/10.48550/arxiv.2606.27864"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.27864","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27864","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.27864","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139581600","display_name":"T\\=\u0131kun \u00d4ng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u00d4ng, T\u012bkun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139583582","display_name":"Georg B\u00f6kman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"B\u00f6kman, Georg","raw_affiliation_strings":[],"raw_orcid":null,"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":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/T11094","display_name":"Face Recognition and Perception","score":0.28209999203681946,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.28209999203681946,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.08240000158548355,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11887","display_name":"Quasicrystal Structures and Properties","score":0.07190000265836716,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/equivariant-map","display_name":"Equivariant map","score":0.933899998664856},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6503000259399414},{"id":"https://openalex.org/keywords/homogeneous-space","display_name":"Homogeneous space","score":0.5587999820709229},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.3580000102519989},{"id":"https://openalex.org/keywords/symmetry-group","display_name":"Symmetry group","score":0.3409999907016754},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.3249000012874603}],"concepts":[{"id":"https://openalex.org/C171036898","wikidata":"https://www.wikidata.org/wiki/Q256355","display_name":"Equivariant map","level":2,"score":0.933899998664856},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6503000259399414},{"id":"https://openalex.org/C96469262","wikidata":"https://www.wikidata.org/wiki/Q1324364","display_name":"Homogeneous space","level":2,"score":0.5587999820709229},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5539000034332275},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.4287000000476837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3725999891757965},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C44306375","wikidata":"https://www.wikidata.org/wiki/Q902019","display_name":"Symmetry group","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.32179999351501465},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.310699999332428},{"id":"https://openalex.org/C187915474","wikidata":"https://www.wikidata.org/wiki/Q622679","display_name":"Lie group","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29429998993873596},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.2870999872684479},{"id":"https://openalex.org/C134786449","wikidata":"https://www.wikidata.org/wiki/Q3391255","display_name":"Planar","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26429998874664307},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C2776394503","wikidata":"https://www.wikidata.org/wiki/Q5282063","display_name":"Discrete symmetry","level":3,"score":0.2597000002861023}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.27864","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27864","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.27864","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27864","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision":[0],"transformers":[1,32],"have":[2],"become":[3],"a":[4,28,41,117],"dominant":[5],"architecture":[6,126],"for":[7,66],"visual":[8,197],"recognition.":[9],"However,":[10],"standard":[11],"models":[12,136],"do":[13],"not":[14],"explicitly":[15],"encode":[16],"the":[17,58,67,79,87,97,100,125,134,138,163,170],"planar":[18],"symmetries":[19],"that":[20,44,74,181],"arise":[21],"in":[22,96,143,169],"many":[23],"vision":[24,31],"domains.":[25],"We":[26,92,114,132],"introduce":[27],"family":[29],"of":[30,38,57,81,89,149,165,190],"equivariant":[33,55,102,157],"to":[34],"arbitrary":[35],"discrete":[36,192],"subgroups":[37,148],"$\\mathrm{O}(2)$,":[39],"providing":[40],"unified":[42],"framework":[43],"generalizes":[45],"prior":[46],"flipping-":[47],"and":[48,151,160],"$D_4$-equivariant":[49],"transformer":[50,60],"architectures.":[51],"Our":[52,153],"construction":[53],"yields":[54],"analogues":[56],"core":[59],"components,":[61],"together":[62],"with":[63,128],"expressivity":[64],"guarantees":[65],"resulting":[68,135],"layers.":[69],"In":[70],"particular,":[71],"we":[72],"show":[73],"whenever":[75],"$H":[76],"\\le":[77],"G$,":[78],"class":[80,88],"$G$-equivariant":[82,107],"ViTs":[83],"embeds":[84],"naturally":[85],"into":[86],"$H$-equivariant":[90],"ViTs.":[91],"also":[93],"prove":[94],"that,":[95],"single-head":[98],"setting,":[99],"corresponding":[101],"self-attention":[103,108],"layer":[104],"realizes":[105],"every":[106],"map":[109],"representable":[110],"by":[111],"ordinary":[112],"self-attention.":[113],"further":[115,188],"construct":[116],"$D_6$-equivariant":[118],"model":[119],"based":[120],"on":[121,137],"hexagonal":[122],"patches,":[123],"making":[124],"compatible":[127],"six-fold":[129],"rotational":[130],"symmetries.":[131],"evaluate":[133],"PatternNet":[139],"aerial":[140],"image":[141],"dataset":[142],"artificially":[144],"data-scarce":[145],"regimes":[146],"across":[147],"$D_4$":[150],"$D_6$.":[152],"experiments":[154],"compare":[155],"two":[156],"attention":[158],"mechanisms":[159],"analyze":[161],"how":[162,191],"choice":[164],"homogeneous-space":[166],"configurations":[167],"used":[168],"nonlinearities":[171],"affects":[172],"performance.":[173],"Preliminary":[174],"results":[175],"under":[176],"matched":[177],"parameter":[178],"budgets":[179],"indicate":[180],"equivariance":[182],"can":[183],"improve":[184],"recognition":[185,198],"accuracy,":[186],"motivating":[187],"study":[189],"symmetry":[193],"groups":[194],"shape":[195],"transformer-based":[196],"models.":[199]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-30T00:00:00"}
