{"id":"https://openalex.org/W4413800879","doi":"https://doi.org/10.1007/s40747-025-02043-z","title":"SAG-ViT: a scale-aware, high-fidelity patching approach with graph attention for vision transformers","display_name":"SAG-ViT: a scale-aware, high-fidelity patching approach with graph attention for vision transformers","publication_year":2025,"publication_date":"2025-08-28","ids":{"openalex":"https://openalex.org/W4413800879","doi":"https://doi.org/10.1007/s40747-025-02043-z"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-025-02043-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-02043-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-02043-z.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-02043-z.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shravan Venkatraman","orcid":null},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Shravan Venkatraman","raw_affiliation_strings":["School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India","institution_ids":["https://openalex.org/I876193797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020581858","display_name":"Jaskaran Singh Walia","orcid":null},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jaskaran Singh Walia","raw_affiliation_strings":["School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India","institution_ids":["https://openalex.org/I876193797"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041284519","display_name":"P. R. Joe Dhanith","orcid":"https://orcid.org/0000-0002-9022-9145"},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"P. R. Joe Dhanith","raw_affiliation_strings":["School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India","institution_ids":["https://openalex.org/I876193797"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I876193797"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":4.6519,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.9525934,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"11","issue":"10","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9990000128746033,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9954000115394592,"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/fidelity","display_name":"Fidelity","score":0.6836600303649902},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.6385837197303772},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5536834597587585},{"id":"https://openalex.org/keywords/computational-intelligence","display_name":"Computational intelligence","score":0.5299870371818542},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5238309502601624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3628724217414856},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21921998262405396},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10926726460456848},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08684051036834717}],"concepts":[{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6836600303649902},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.6385837197303772},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5536834597587585},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.5299870371818542},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5238309502601624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3628724217414856},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21921998262405396},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10926726460456848},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08684051036834717},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-025-02043-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-02043-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-02043-z.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4493b80edc194bd8a3efc083e2fee1c7","is_oa":true,"landing_page_url":"https://doaj.org/article/4493b80edc194bd8a3efc083e2fee1c7","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 11, Iss 10, Pp 1-21 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-025-02043-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-02043-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-02043-z.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320319346","display_name":"Vellore Institute of Technology, Chennai","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413800879.pdf","grobid_xml":"https://content.openalex.org/works/W4413800879.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W2067713319","https://openalex.org/W2097117768","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2592962403","https://openalex.org/W2618530766","https://openalex.org/W2809418595","https://openalex.org/W2883780447","https://openalex.org/W2907492528","https://openalex.org/W2963091558","https://openalex.org/W2963163009","https://openalex.org/W2963446712","https://openalex.org/W2988396473","https://openalex.org/W3096609285","https://openalex.org/W3121523901","https://openalex.org/W3138516171","https://openalex.org/W3151130473","https://openalex.org/W3172509117","https://openalex.org/W3190492058","https://openalex.org/W4214493665","https://openalex.org/W4214588794","https://openalex.org/W4312443924","https://openalex.org/W4312769131","https://openalex.org/W4312785838","https://openalex.org/W4312950730","https://openalex.org/W4386529059","https://openalex.org/W4387211438","https://openalex.org/W4394862932","https://openalex.org/W4399418520","https://openalex.org/W4399873910","https://openalex.org/W4400188495","https://openalex.org/W4400229603","https://openalex.org/W4403071477","https://openalex.org/W4403071488","https://openalex.org/W4403071762","https://openalex.org/W4404194473","https://openalex.org/W4409217717","https://openalex.org/W4410274499","https://openalex.org/W4410294729","https://openalex.org/W4410838589"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4293777179","https://openalex.org/W4385452045","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995","https://openalex.org/W2332512904","https://openalex.org/W4224231624","https://openalex.org/W2319626700"],"abstract_inverted_index":{"Abstract":[0],"Vision":[1],"Transformers":[2],"(ViTs)":[3],"have":[4,47],"redefined":[5],"image":[6,19,181],"classification":[7,182],"by":[8,53,167],"leveraging":[9,54],"self-attention":[10],"to":[11,106,126,132,197],"capture":[12],"complex":[13,175],"patterns":[14],"and":[15,103,147,174,193,207],"long-range":[16,172],"dependencies":[17,173],"between":[18],"patches.":[20],"However,":[21],"a":[22,85,114,143,151,168],"key":[23],"challenge":[24],"for":[25],"ViTs":[26],"is":[27,34,164],"efficiently":[28],"incorporating":[29],"multi-scale":[30,93,119],"feature":[31,94,120,148],"representations,":[32],"which":[33],"inherent":[35],"in":[36,50],"convolutional":[37],"neural":[38],"networks":[39],"(CNNs)":[40],"through":[41],"their":[42],"hierarchical":[43],"structure.":[44],"Graph":[45,87,152],"transformers":[46],"made":[48],"strides":[49],"addressing":[51],"this":[52,80],"graph-based":[55],"modeling,":[56],"but":[57],"they":[58],"often":[59],"lose":[60],"or":[61,69],"insufficiently":[62],"represent":[63],"spatial":[64,146],"hierarchies,":[65],"especially":[66],"since":[67],"redundant":[68],"less":[70],"relevant":[71],"areas":[72],"dilute":[73],"the":[74,92,98,116,135,157],"image\u2019s":[75],"contextual":[76,109],"representation.":[77,110],"To":[78],"bridge":[79],"gap,":[81],"we":[82],"propose":[83],"SAG-ViT,":[84],"Scale-Aware":[86],"Attention":[88,153],"ViT":[89],"that":[90],"integrates":[91],"capabilities":[95],"of":[96,101,189],"CNNs,":[97],"representational":[99],"power":[100],"ViTs,":[102],"graph-attended":[104],"patching":[105,134],"enable":[107],"richer":[108,128],"Using":[111],"EfficientNetV2":[112],"as":[113],"backbone,":[115],"model":[117],"extracts":[118],"maps,":[121],"dividing":[122],"them":[123],"into":[124,142],"patches":[125,139],"preserve":[127],"semantic":[129],"information":[130],"compared":[131],"directly":[133],"input":[136],"images.":[137],"The":[138],"are":[140,209],"structured":[141],"graph":[144,162],"using":[145],"similarities,":[149],"where":[150],"Network":[154],"(GAT)":[155],"refines":[156],"node":[158],"embeddings.":[159],"This":[160],"refined":[161],"representation":[163],"then":[165],"processed":[166],"Transformer":[169],"encoder,":[170],"capturing":[171],"interactions.":[176],"Evaluated":[177],"on":[178,191,195],"six":[179],"diverse":[180],"benchmarks,":[183],"SAG-ViT":[184],"achieves":[185],"an":[186],"F1":[187],"score":[188],"0.9574":[190],"CIFAR-10":[192],"0.9958":[194],"GTSRB,":[196],"validate":[198],"its":[199],"consistent":[200],"improvements":[201],"across":[202],"multiple":[203],"backbones.":[204],"Our":[205],"code":[206],"weights":[208],"available":[210],"at":[211],"https://github.com/shravan-18/SAG-ViT":[212],".":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}