{"id":"https://openalex.org/W7140102886","doi":"https://doi.org/10.48550/arxiv.2603.19496","title":"VeloxNet: Efficient Spatial Gating for Lightweight Embedded Image Classification","display_name":"VeloxNet: Efficient Spatial Gating for Lightweight Embedded Image Classification","publication_year":2026,"publication_date":"2026-03-19","ids":{"openalex":"https://openalex.org/W7140102886","doi":"https://doi.org/10.48550/arxiv.2603.19496"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.19496","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19496","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2603.19496","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130370439","display_name":"Md Meftahul Ferdaus","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ferdaus, Md Meftahul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008394543","display_name":"Elias Ioup","orcid":"https://orcid.org/0009-0002-3699-6762"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ioup, Elias","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130377261","display_name":"Mahdi Abdelguerfi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdelguerfi, Mahdi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055421257","display_name":"Anton Netchaev","orcid":"https://orcid.org/0000-0002-8463-1779"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Netchaev, Anton","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130369276","display_name":"Steven Sloan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sloan, Steven","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130345824","display_name":"Ken Pathak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pathak, Ken","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5093225472","display_name":"Kendall N. Niles","orcid":"https://orcid.org/0009-0007-2925-8856"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niles, Kendall N.","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/T12597","display_name":"Fire Detection and Safety Systems","score":0.3682999908924103,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/T12597","display_name":"Fire Detection and Safety Systems","score":0.3682999908924103,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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":0.30649998784065247,"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/T11606","display_name":"Infrastructure Maintenance and Monitoring","score":0.08269999921321869,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.7321000099182129},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6287999749183655},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5616000294685364},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5102999806404114},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.4756999909877777},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4715999960899353},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.43380001187324524},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43220001459121704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7903000116348267},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.7321000099182129},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6287999749183655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.572700023651123},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5616000294685364},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5102999806404114},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.4756999909877777},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4715999960899353},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.43380001187324524},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43220001459121704},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4097999930381775},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35910001397132874},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.33570000529289246},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3052999973297119},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29660001397132874},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.19496","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19496","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2603.19496","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19496","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":{"Deploying":[0],"deep":[1],"learning":[2],"models":[3],"on":[4,25,117,175,178,182],"embedded":[5,51],"devices":[6],"for":[7,50,126,204],"tasks":[8],"such":[9],"as":[10],"aerial":[11,119],"disaster":[12],"monitoring":[13],"and":[14,29,68,135,150,180,201],"infrastructure":[15],"inspection":[16],"requires":[17],"architectures":[18],"that":[19,39,63,187],"balance":[20],"accuracy":[21,200],"with":[22,44,111,192],"strict":[23],"constraints":[24],"model":[26],"size,":[27],"memory,":[28],"latency.":[30],"This":[31],"paper":[32],"introduces":[33],"VeloxNet,":[34],"a":[35,58,84],"lightweight":[36],"CNN":[37],"architecture":[38],"replaces":[40],"SqueezeNet's":[41],"fire":[42,88],"modules":[43,191],"gated":[45],"multi-layer":[46],"perceptron":[47],"(gMLP)":[48],"blocks":[49,195],"image":[52,120],"classification.":[53],"Each":[54],"gMLP":[55],"block":[56],"uses":[57],"spatial":[59,66,76,106,193],"gating":[60,194],"unit":[61],"(SGU)":[62],"applies":[64],"learned":[65],"projections":[67],"multiplicative":[69],"gating,":[70],"enabling":[71],"the":[72,79,102,122,130,136,156,218],"network":[73],"to":[74,93,162,166],"capture":[75],"dependencies":[77],"across":[78],"full":[80],"feature":[81],"map":[82],"in":[83],"single":[85],"layer.":[86],"Unlike":[87],"modules,":[89],"which":[90],"are":[91],"limited":[92],"local":[94,189],"receptive":[95],"fields":[96],"defined":[97],"by":[98,159,173],"small":[99],"convolutional":[100,190],"kernels,":[101],"SGU":[103],"provides":[104],"global":[105],"modeling":[107],"at":[108],"each":[109],"layer":[110],"fewer":[112],"parameters.":[113],"We":[114],"evaluate":[115],"VeloxNet":[116,154],"three":[118],"datasets:":[121],"Aerial":[123],"Image":[124],"Database":[125],"Emergency":[127],"Response":[128],"(AIDER),":[129],"Comprehensive":[131],"Disaster":[132],"Dataset":[133,139],"(CDD),":[134],"Levee":[137],"Defect":[138],"(LDD),":[140],"comparing":[141],"against":[142],"eleven":[143],"baselines":[144],"including":[145],"MobileNet":[146],"variants,":[147],"ShuffleNet,":[148],"EfficientNet,":[149],"recent":[151],"vision":[152],"transformers.":[153],"reduces":[155],"parameter":[157,202],"count":[158],"46.1%":[160],"relative":[161],"SqueezeNet":[163],"(from":[164],"740,970":[165],"399,366)":[167],"while":[168],"improving":[169],"weighted":[170],"F1":[171],"scores":[172],"6.32%":[174],"AIDER,":[176],"30.83%":[177],"CDD,":[179],"2.51%":[181],"LDD.":[183],"These":[184],"results":[185],"demonstrate":[186],"substituting":[188],"can":[196],"improve":[197],"both":[198],"classification":[199],"efficiency":[203],"resource-constrained":[205],"deployment.":[206],"The":[207],"source":[208],"code":[209],"will":[210],"be":[211],"made":[212],"publicly":[213],"available":[214],"upon":[215],"acceptance":[216],"of":[217],"paper.":[219]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-24T00:00:00"}