{"id":"https://openalex.org/W4416243771","doi":"https://doi.org/10.1109/iccv51701.2025.01945","title":"UniConvNet: Expanding Effective Receptive Field While Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale","display_name":"UniConvNet: Expanding Effective Receptive Field While Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416243771","doi":"https://doi.org/10.1109/iccv51701.2025.01945"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.09000","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100370107","display_name":"Yuhao Wang","orcid":"https://orcid.org/0000-0002-9863-273X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Wang","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101118273","display_name":"Wei Xi","orcid":"https://orcid.org/0009-0000-4720-7875"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xi","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20922","last_page":"20933"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7232000231742859,"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":0.7232000231742859,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.044199999421834946,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.028300000354647636,"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/scalability","display_name":"Scalability","score":0.5683000087738037},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5644999742507935},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.5315999984741211},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5196999907493591},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.517300009727478},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45989999175071716},{"id":"https://openalex.org/keywords/receptive-field","display_name":"Receptive field","score":0.453900009393692},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4399999976158142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6898999810218811},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5683000087738037},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5644999742507935},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.5315999984741211},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5196999907493591},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4984000027179718},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45989999175071716},{"id":"https://openalex.org/C19071747","wikidata":"https://www.wikidata.org/wiki/Q1755207","display_name":"Receptive field","level":2,"score":0.453900009393692},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4399999976158142},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4343000054359436},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4101000130176544},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.4083999991416931},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C146168522","wikidata":"https://www.wikidata.org/wiki/Q1068239","display_name":"Radiosity (computer graphics)","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.3167000114917755},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3019999861717224},{"id":"https://openalex.org/C134765980","wikidata":"https://www.wikidata.org/wiki/Q879126","display_name":"Bitwise operation","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.09000","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.09000","pdf_url":"https://arxiv.org/pdf/2508.09000","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.09000","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.09000","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.09000","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.09000","pdf_url":"https://arxiv.org/pdf/2508.09000","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":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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(ConvNets)":[3],"with":[4,161,171],"large":[5,46,186],"effective":[6,51],"receptive":[7,95],"field":[8],"(ERF),":[9],"still":[10],"in":[11],"their":[12],"early":[13],"stages,":[14],"have":[15],"demonstrated":[16],"promising":[17],"effectiveness":[18],"while":[19,58,115],"constrained":[20],"by":[21,63],"high":[22],"parameters":[23,173],"and":[24,27,52,82,140,148,158,174,185,195],"FLOPs":[25],"costs":[26],"disrupted":[28],"asymptotically":[29],"Gaussian":[30],"distribution":[31],"(AGD)":[32],"of":[33,61,66,94,105,112,118,130],"ERF.":[34,119],"This":[35,74],"paper":[36,75],"proposes":[37],"an":[38],"alternative":[39],"paradigm:":[40],"rather":[41],"than":[42],"merely":[43],"employing":[44],"extremely":[45],"ERF,":[47],"it":[48],"is":[49],"more":[50],"efficient":[53],"to":[54,102,182],"expand":[55],"the":[56,88,92,103,110],"ERF":[57,62,98],"maintaining":[59,116],"AGD":[60,117],"proper":[64],"combination":[65],"smaller":[67],"kernels,":[68],"such":[69],"as":[70,87],"$7\\times{7}$,":[71],"$9\\times{9}$,":[72],"$11\\times{11}$.":[73],"introduces":[76],"a":[77,84,125],"Three-layer":[78],"Receptive":[79],"Field":[80],"Aggregator":[81],"designs":[83],"Layer":[85],"Operator":[86],"fundamental":[89],"operator":[90],"from":[91],"perspective":[93],"field.":[96],"The":[97],"can":[99],"be":[100],"expanded":[101],"level":[104],"existing":[106],"large-kernel":[107],"ConvNets":[108],"through":[109],"stack":[111],"proposed":[113],"modules":[114],"Using":[120],"these":[121],"designs,":[122],"we":[123],"propose":[124],"universal":[126],"model":[127],"for":[128,155],"ConvNet":[129],"any":[131],"scale,":[132],"termed":[133],"UniConvNet.":[134],"Extensive":[135],"experiments":[136],"on":[137,192],"ImageNet-1K,":[138],"COCO2017,":[139],"ADE20K":[141],"demonstrate":[142],"that":[143],"UniConvNet":[144],"outperforms":[145],"state-of-the-art":[146],"CNNs":[147],"ViTs":[149],"across":[150],"various":[151],"vision":[152],"recognition":[153],"tasks":[154],"both":[156],"lightweight":[157],"large-scale":[159],"models":[160,196],"comparable":[162],"throughput.":[163],"Surprisingly,":[164],"UniConvNet-T":[165],"achieves":[166],"$84.2\\%$":[167],"ImageNet":[168],"top-1":[169,190],"accuracy":[170,191],"$30M$":[172],"$5.1G$":[175],"FLOPs.":[176],"UniConvNet-XL":[177],"also":[178],"shows":[179],"competitive":[180],"scalability":[181],"big":[183],"data":[184],"models,":[187],"acquiring":[188],"$88.4\\%$":[189],"ImageNet.":[193],"Code":[194],"are":[197],"publicly":[198],"available":[199],"at":[200],"https://github.com/ai-paperwithcode/UniConvNet.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}