{"id":"https://openalex.org/W7160249329","doi":"https://doi.org/10.1109/wacv61042.2026.00407","title":"STEG-AIW: Spatio-Temporal Gating and Adaptive-Timestep Inference for Efficient Spiking Neural Networks","display_name":"STEG-AIW: Spatio-Temporal Gating and Adaptive-Timestep Inference for Efficient Spiking Neural Networks","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160249329","doi":"https://doi.org/10.1109/wacv61042.2026.00407"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","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":"https://openalex.org/A5130934592","display_name":"Gulfam Ahmed Saju","orcid":null},"institutions":[{"id":"https://openalex.org/I100633361","display_name":"University of Massachusetts Dartmouth","ror":"https://ror.org/00fzmm222","country_code":"US","type":"education","lineage":["https://openalex.org/I100633361"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gulfam Ahmed Saju","raw_affiliation_strings":["University of Massachusetts Dartmouth,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Dartmouth,USA","institution_ids":["https://openalex.org/I100633361"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053428537","display_name":"Anton Spirkin","orcid":"https://orcid.org/0000-0002-3969-4391"},"institutions":[{"id":"https://openalex.org/I2799471739","display_name":"Naval Undersea Warfare Center","ror":"https://ror.org/04bnxa153","country_code":"US","type":"other","lineage":["https://openalex.org/I1328969757","https://openalex.org/I1330347796","https://openalex.org/I2799471739","https://openalex.org/I3130687028"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anton Spirkin","raw_affiliation_strings":["Naval Undersea Warfare Center Newport Division,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naval Undersea Warfare Center Newport Division,USA","institution_ids":["https://openalex.org/I2799471739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135403496","display_name":"Felipe Marcelino","orcid":null},"institutions":[{"id":"https://openalex.org/I2799471739","display_name":"Naval Undersea Warfare Center","ror":"https://ror.org/04bnxa153","country_code":"US","type":"other","lineage":["https://openalex.org/I1328969757","https://openalex.org/I1330347796","https://openalex.org/I2799471739","https://openalex.org/I3130687028"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felipe Marcelino","raw_affiliation_strings":["Naval Undersea Warfare Center Newport Division,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naval Undersea Warfare Center Newport Division,USA","institution_ids":["https://openalex.org/I2799471739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5096930449","display_name":"\u957f\u5b87 \u4ec7","orcid":null},"institutions":[{"id":"https://openalex.org/I100633361","display_name":"University of Massachusetts Dartmouth","ror":"https://ror.org/00fzmm222","country_code":"US","type":"education","lineage":["https://openalex.org/I100633361"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuchou Chang","raw_affiliation_strings":["University of Massachusetts Dartmouth,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Dartmouth,USA","institution_ids":["https://openalex.org/I100633361"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"4180","last_page":"4189"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.8860999941825867,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.8860999941825867,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.029500000178813934,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.017000000923871994,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spiking-neural-network","display_name":"Spiking neural network","score":0.4410000145435333},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4377000033855438},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.42910000681877136},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4000000059604645},{"id":"https://openalex.org/keywords/gating","display_name":"Gating","score":0.3409000039100647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6913999915122986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5802000164985657},{"id":"https://openalex.org/C11731999","wikidata":"https://www.wikidata.org/wiki/Q9067355","display_name":"Spiking neural network","level":3,"score":0.4410000145435333},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C194544171","wikidata":"https://www.wikidata.org/wiki/Q21105679","display_name":"Gating","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C2781390188","wikidata":"https://www.wikidata.org/wiki/Q25203449","display_name":"Spike (software development)","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2761000096797943},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2711000144481659},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26899999380111694}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2006370340","https://openalex.org/W2039573396","https://openalex.org/W2108598243","https://openalex.org/W2109596721","https://openalex.org/W2130459697","https://openalex.org/W2163630896","https://openalex.org/W2170968634","https://openalex.org/W2485907003","https://openalex.org/W2513853720","https://openalex.org/W2619510810","https://openalex.org/W2621826044","https://openalex.org/W2745933219","https://openalex.org/W2752782242","https://openalex.org/W2798878556","https://openalex.org/W2939020224","https://openalex.org/W2962677625","https://openalex.org/W3014020978","https://openalex.org/W3102750118","https://openalex.org/W3196512642","https://openalex.org/W3200038452","https://openalex.org/W4210357113","https://openalex.org/W4224920348","https://openalex.org/W4319866562","https://openalex.org/W4367043296","https://openalex.org/W4386763804","https://openalex.org/W4389331480","https://openalex.org/W4390871967","https://openalex.org/W4390872397","https://openalex.org/W4390873999","https://openalex.org/W4392843798","https://openalex.org/W4394698802","https://openalex.org/W4408818595","https://openalex.org/W4409262873","https://openalex.org/W4409363287","https://openalex.org/W4413147369","https://openalex.org/W4413147698","https://openalex.org/W7133183292","https://openalex.org/W7133206442"],"related_works":[],"abstract_inverted_index":{"Spiking":[0],"neural":[1],"networks":[2],"(SNNs)":[3],"are":[4],"efficient,":[5],"yet":[6],"modern":[7],"systems":[8],"still":[9],"waste":[10],"compute":[11],"by":[12,20],"propagating":[13],"redundant":[14],"activations":[15,60],"within":[16],"a":[17,22,34,49,90,107,162],"timestep":[18],"and":[19,36,74,106,154],"using":[21],"fixed":[23],"temporal":[24,63],"horizon":[25],"regardless":[26],"of":[27,104],"input":[28],"difficulty.":[29],"We":[30,84],"present":[31],"STEG\u2013":[32],"AIW,":[33],"training":[35],"inference":[37],"framework":[38],"that":[39,92],"addresses":[40],"both":[41],"issues.":[42],"The":[43,65],"Spatio-Temporal":[44],"Efficient":[45],"Gate":[46],"(STEG)":[47],"is":[48],"lightweight":[50],"gating":[51],"module":[52,70],"placed":[53],"at":[54],"residual":[55],"stages.":[56],"It":[57],"suppresses":[58],"non-salient":[59],"while":[61],"preserving":[62],"dynamics.":[64],"Adaptive":[66],"Inference":[67],"Window":[68],"(AIW)":[69],"accumulates":[71],"per-timestep":[72],"evidence":[73],"converts":[75],"it":[76,143],"to":[77,100,120,165,173],"halting":[78],"probabilities":[79],"for":[80],"sample-wise":[81],"early":[82],"termination.":[83],"train":[85],"the":[86,101,137,147],"model":[87],"end-to-end":[88],"with":[89,132,150],"loss":[91],"balances":[93],"task":[94],"accuracy,":[95],"an":[96],"efficiency":[97],"term":[98,109],"proportional":[99],"expected":[102],"number":[103],"timesteps,":[105],"sparsity":[108],"on":[110],"gate":[111],"activations.":[112],"A":[113],"simple":[114],"complexity":[115],"analysis":[116],"links":[117],"these":[118],"choices":[119],"fewer":[121,134,152],"synaptic":[122,156],"operations.":[123],"On":[124,140],"static":[125],"image":[126],"benchmarks,":[127],"STEG\u2013AIW":[128,160],"attains":[129],"state-of-the-art":[130],"accuracy":[131,149],"34\u201388%":[133],"timesteps":[135,153],"than":[136],"strongest":[138],"baselines.":[139],"neuromorphic":[141],"datasets,":[142],"matches":[144],"or":[145],"exceeds":[146],"best":[148],"43\u201373%":[151],"reduces":[155],"operations":[157],"accordingly.":[158],"Overall,":[159],"provides":[161],"backbone-agnostic":[163],"path":[164],"accurate,":[166],"low-power":[167],"inference.":[168],"This":[169],"moves":[170],"SNNs":[171],"closer":[172],"practical":[174],"deployment.":[175]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}