{"id":"https://openalex.org/W4416516265","doi":"https://doi.org/10.48550/arxiv.2506.23532","title":"GViT: Representing Images as Gaussians for Visual Recognition","display_name":"GViT: Representing Images as Gaussians for Visual Recognition","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416516265","doi":"https://doi.org/10.48550/arxiv.2506.23532"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.23532","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.23532","pdf_url":"https://arxiv.org/pdf/2506.23532","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.23532","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067752616","display_name":"Jefferson Hernandez","orcid":"https://orcid.org/0000-0002-7091-0478"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hernandez, Jefferson","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050905744","display_name":"Ruozhen He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Ruozhen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081710525","display_name":"Guha Balakrishnan","orcid":"https://orcid.org/0000-0001-8703-1368"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Balakrishnan, Guha","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104361813","display_name":"Alexander C. Berg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Berg, Alexander C.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027328044","display_name":"Vicente Ord\u00f3\u00f1ez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ordonez, Vicente","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5067752616"],"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/T10036","display_name":"Advanced Neural Network Applications","score":0.5462999939918518,"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":0.5462999939918518,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0763000026345253,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.07360000163316727,"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/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6304000020027161},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5946000218391418},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.57669997215271},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5145999789237976},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4372999966144562},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.43549999594688416},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.3691999912261963},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.3549000024795532}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.776199996471405},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.667900025844574},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6304000020027161},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5946000218391418},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.57669997215271},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5296000242233276},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5145999789237976},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.43549999594688416},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3549000024795532},{"id":"https://openalex.org/C2778701210","wikidata":"https://www.wikidata.org/wiki/Q28130034","display_name":"Constructive","level":3,"score":0.352400004863739},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.3084999918937683},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.28459998965263367},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C2779679900","wikidata":"https://www.wikidata.org/wiki/Q25304431","display_name":"Saliency map","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2506.23532","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.23532","pdf_url":"https://arxiv.org/pdf/2506.23532","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2506.23532","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.23532","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.23532","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.23532","pdf_url":"https://arxiv.org/pdf/2506.23532","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,54,77],"introduce":[1],"GVIT,":[2],"a":[3,18,30,45,69,91,101,106,113],"classification":[4],"framework":[5],"that":[6,79],"abandons":[7],"conventional":[8],"pixel":[9],"or":[10],"patch":[11],"grid":[12],"input":[13,83],"representations":[14,84],"in":[15],"favor":[16],"of":[17,21,51,100],"compact":[19],"set":[20],"learnable":[22],"2D":[23,81],"Gaussians.":[24],"Each":[25],"image":[26,74],"is":[27],"encoded":[28],"as":[29,59],"few":[31],"hundred":[32],"Gaussians":[33,64],"whose":[34],"positions,":[35],"scales,":[36],"orientations,":[37],"colors,":[38],"and":[39],"opacities":[40],"are":[41],"optimized":[42],"jointly":[43],"with":[44,86],"ViT":[46,94],"classifier":[47,57],"trained":[48],"on":[49,110],"top":[50],"these":[52],"representations.":[53],"reuse":[55],"the":[56,63,98],"gradients":[58],"constructive":[60],"guidance,":[61,89],"steering":[62],"toward":[65],"class-salient":[66],"regions":[67],"while":[68],"differentiable":[70],"renderer":[71],"optimizes":[72],"an":[73],"reconstruction":[75],"loss.":[76],"demonstrate":[78],"by":[80],"Gaussian":[82],"coupled":[85],"our":[87],"GVIT":[88],"using":[90,112],"relatively":[92],"standard":[93],"architecture,":[95],"closely":[96],"matches":[97],"performance":[99],"traditional":[102],"patch-based":[103],"ViT,":[104],"reaching":[105],"76.9%":[107],"top-1":[108],"accuracy":[109],"Imagenet-1k":[111],"ViT-B":[114],"architecture.":[115]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}