{"id":"https://openalex.org/W4403792536","doi":"https://doi.org/10.1145/3664647.3680872","title":"SI-BiViT: Binarizing Vision Transformers with Spatial Interaction","display_name":"SI-BiViT: Binarizing Vision Transformers with Spatial Interaction","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792536","doi":"https://doi.org/10.1145/3664647.3680872"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680872","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680872","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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":null,"display_name":"Peng Yin","orcid":"https://orcid.org/0009-0005-5753-7794"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peng Yin","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0005-5753-7794","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079828357","display_name":"Xiaosu Zhu","orcid":"https://orcid.org/0000-0001-7728-2518"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaosu Zhu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-7728-2518","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2549-8322","affiliations":[{"raw_affiliation_string":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2522-6394","affiliations":[{"raw_affiliation_string":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]},{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["University of Electronic Science and Technology of China & Tongji University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China & Tongji University, Chengdu, China","institution_ids":["https://openalex.org/I150229711","https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.4006,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62337822,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"8169","last_page":"8178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9977999925613403,"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"}},"topics":[{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9977999925613403,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10036","display_name":"Advanced Neural Network Applications","score":0.9969000220298767,"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/computer-science","display_name":"Computer science","score":0.5438523888587952},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5119448900222778},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46372196078300476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34797969460487366},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3309818506240845},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1847766935825348},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1809723973274231},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07939296960830688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5438523888587952},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5119448900222778},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46372196078300476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34797969460487366},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3309818506240845},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1847766935825348},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1809723973274231},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07939296960830688}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680872","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680872","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2300242332","https://openalex.org/W2559655401","https://openalex.org/W2612690371","https://openalex.org/W2618939455","https://openalex.org/W2887447938","https://openalex.org/W2963150697","https://openalex.org/W2964241181","https://openalex.org/W2982344224","https://openalex.org/W2999905431","https://openalex.org/W3034297393","https://openalex.org/W3040035712","https://openalex.org/W3088524643","https://openalex.org/W3104151879","https://openalex.org/W3117765988","https://openalex.org/W3121523901","https://openalex.org/W3138251877","https://openalex.org/W3138516171","https://openalex.org/W3157506437","https://openalex.org/W3174402370","https://openalex.org/W3211787299","https://openalex.org/W4247924304","https://openalex.org/W4281489207","https://openalex.org/W4281708609","https://openalex.org/W4283809036","https://openalex.org/W4283811336","https://openalex.org/W4304099159","https://openalex.org/W4306177171","https://openalex.org/W4306295203","https://openalex.org/W4307970729","https://openalex.org/W4312453657","https://openalex.org/W4312677967","https://openalex.org/W4312709167","https://openalex.org/W4312726009","https://openalex.org/W4313069943","https://openalex.org/W4385958936","https://openalex.org/W4386072014","https://openalex.org/W4390874319","https://openalex.org/W6783467810","https://openalex.org/W6797854001","https://openalex.org/W6931259419"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Binarized":[0,155],"Vision":[1,13],"Transformers":[2,14],"(BiViTs)":[3],"aim":[4],"to":[5,26,30,36,42,62,84,104,141,153,211],"facilitate":[6],"the":[7,23,37,89,99,106,121,130,166,196,212],"efficient":[8],"and":[9,158,169,190],"lightweight":[10],"utilization":[11],"of":[12,64,171,199,205],"(ViTs)":[15],"on":[16],"devices":[17],"with":[18],"limited":[19],"computational":[20],"resources.":[21],"Yet,":[22],"current":[24],"approach":[25,81],"binarizing":[27],"ViT":[28,79,180],"leads":[29],"a":[31,55,78,137],"substantial":[32],"performance":[33,60,198],"decrease":[34],"compared":[35,210],"full-precision":[38],"model,":[39],"posing":[40],"obstacles":[41],"practical":[43],"deployment.":[44],"By":[45],"empirical":[46],"study,":[47],"we":[48,76,135],"reveal":[49],"that":[50,58],"spatial":[51,86,127],"interaction":[52,87,128],"(SI)":[53],"is":[54,96,151],"critical":[56],"factor":[57],"impacts":[59],"due":[61],"lack":[63],"token-level":[65],"correlation,":[66],"but":[67,124],"previous":[68,213],"work":[69],"ignores":[70],"this":[71,74],"factor.":[72],"To":[73],"end,":[75],"design":[77,136],"binarization":[80,90],"dubbed":[82],"SI-BiViT":[83,150,172,194],"incorporate":[85],"in":[88,182,207],"process.":[91],"Specifically,":[92],"an":[93,203],"SI":[94,132],"module":[95,103],"placed":[97],"alongside":[98],"Multi-Layer":[100],"Perceptron":[101],"(MLP)":[102],"formulate":[105],"dual-branch":[107],"structure.":[108],"This":[109],"structure":[110],"not":[111],"only":[112],"leverages":[113],"knowledge":[114],"from":[115],"pre-trained":[116],"ViTs":[117,156,201],"by":[118,173,202],"distilling":[119],"over":[120],"original":[122],"MLP,":[123],"also":[125],"enhances":[126,195],"via":[129],"introduced":[131],"module.":[133],"Correspondingly,":[134],"decoupled":[138],"training":[139],"strategy":[140],"train":[142],"these":[143],"two":[144],"branches":[145],"more":[146],"effectively.":[147],"Importantly,":[148],"our":[149,175],"orthogonal":[152],"existing":[154],"approaches":[157],"can":[159],"be":[160],"directly":[161],"plugged.":[162],"Extensive":[163],"experiments":[164],"demonstrate":[165],"strong":[167],"flexibility":[168],"effectiveness":[170],"plugging":[174],"method":[176],"into":[177],"four":[178],"classic":[179],"backbones":[181],"supporting":[183],"three":[184],"downstream":[185],"tasks,":[186],"including":[187],"classification,":[188],"detection,":[189],"segmentation.":[191],"In":[192],"particular,":[193],"classification":[197],"binarized":[200],"average":[204],"10.52%":[206],"Top-1":[208],"accuracy":[209],"state-of-the-art.":[214],"Codes":[215],"are":[216],"available":[217],"at":[218],"https://github.com/VL-Group/SI-BiViT":[219]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}