{"id":"https://openalex.org/W7164156170","doi":"https://doi.org/10.1109/fccm68464.2026.00041","title":"ImageHD: Energy-Efficient On-Device Continual Learning of Visual Representations via Hyperdimensional Computing","display_name":"ImageHD: Energy-Efficient On-Device Continual Learning of Visual Representations via Hyperdimensional Computing","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7164156170","doi":"https://doi.org/10.1109/fccm68464.2026.00041"},"language":null,"primary_location":{"id":"doi:10.1109/fccm68464.2026.00041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fccm68464.2026.00041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 34th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","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":"https://openalex.org/A5120024873","display_name":"Jebacyril Arockiaraj","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jebacyril Arockiaraj","raw_affiliation_strings":["University of Southern California,Los Angeles,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134529200","display_name":"Dhruv Parikh","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhruv Parikh","raw_affiliation_strings":["University of Southern California,Los Angeles,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138337899","display_name":"Viktor Prasanna","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viktor Prasanna","raw_affiliation_strings":["University of Southern California,Los Angeles,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79248616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"231","last_page":"240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9828000068664551,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9828000068664551,"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":0.009600000455975533,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.0032999999821186066,"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/visualization","display_name":"Visualization","score":0.34619998931884766},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.32589998841285706},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.29760000109672546},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.2969000041484833},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.28519999980926514},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2711000144481659}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6028000116348267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5189999938011169},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2969000041484833},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fccm68464.2026.00041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fccm68464.2026.00041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 34th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7014371752738953,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1579705726","https://openalex.org/W1682403713","https://openalex.org/W2070862086","https://openalex.org/W2520083297","https://openalex.org/W2554616628","https://openalex.org/W2560647685","https://openalex.org/W2565989828","https://openalex.org/W2788388592","https://openalex.org/W2953901595","https://openalex.org/W2963122961","https://openalex.org/W2964189064","https://openalex.org/W2965571038","https://openalex.org/W2971544482","https://openalex.org/W2997106510","https://openalex.org/W3014339660","https://openalex.org/W3030364939","https://openalex.org/W3046803548","https://openalex.org/W3097816393","https://openalex.org/W3125116114","https://openalex.org/W3178193590","https://openalex.org/W3206785724","https://openalex.org/W4213346165","https://openalex.org/W4225777901","https://openalex.org/W4388214769","https://openalex.org/W4392173735","https://openalex.org/W4395666190","https://openalex.org/W4396949463","https://openalex.org/W4402349041","https://openalex.org/W4402703109","https://openalex.org/W4407632991","https://openalex.org/W4409263168","https://openalex.org/W4409670797","https://openalex.org/W4413145698","https://openalex.org/W4414198969","https://openalex.org/W4415795349"],"related_works":[],"abstract_inverted_index":{"On-device":[0],"continual":[1,85,114,130,151,252],"learning":[2,86,115,131,152,253,262],"(CL)":[3],"enables":[4],"edge":[5,21,178],"devices":[6],"to":[7,9,123,176,216,235],"adapt":[8],"non-stationary":[10],"data":[11,118],"streams":[12],"without":[13,139,181],"offline":[14],"retraining,":[15],"which":[16,97],"is":[17,189],"critical":[18],"for":[19,112,258],"real-time":[20],"AI.":[22],"However,":[23],"most":[24],"existing":[25],"CL":[26],"methods":[27],"rely":[28],"on":[29,45,100,120,196,229],"backpropagation-based":[30],"updates":[31],"or":[32],"exemplar-heavy":[33],"classifiers,":[34],"incurring":[35],"high":[36],"compute,":[37],"memory,":[38],"and":[39,93,135,164,207,239],"latency":[40,134],"overheads":[41],"that":[42,154],"hinder":[43],"deployment":[44,99,179],"resource-constrained":[46,101],"devices.":[47],"Hyperdimensional":[48],"Computing":[49],"(HDC)":[50],"offers":[51],"an":[52,109],"alternative":[53],"by":[54],"enabling":[55],"fast,":[56],"non-iterative":[57],"online":[58],"updates.":[59],"When":[60],"paired":[61],"with":[62,76],"a":[63,149,160,165,172,192,255],"lightweight":[64],"convolutional":[65],"neural":[66],"network":[67],"(CNN)":[68],"feature":[69],"extractor,":[70],"HDC":[71],"supports":[72],"efficient":[73],"on-device":[74,113,260],"adaptation":[75],"strong":[77],"visual":[78,117],"representations.":[79],"Despite":[80],"this":[81,104],"progress,":[82],"prior":[83],"HDC-based":[84],"systems":[87],"typically":[88],"employ":[89],"multi-tier":[90],"memory":[91,137,163],"hierarchies":[92],"complex":[94],"cluster":[95,167,209],"management,":[96],"complicate":[98],"hardware":[102],"platforms.In":[103],"paper,":[105],"we":[106,147],"propose":[107],"ImageHD,":[108],"FPGA":[110],"accelerator":[111],"of":[116],"based":[119],"HDC,":[121],"designed":[122],"address":[124],"these":[125],"limitations.":[126],"ImageHD":[127,188],"targets":[128],"streaming":[129,193],"under":[132],"strict":[133],"on-chip":[136,224],"constraints,":[138],"expensive":[140],"iterative":[141],"optimization.":[142],"At":[143,184],"the":[144,185,197,230],"algorithmic":[145],"level,":[146,187],"introduce":[148],"hardware-optimized":[150],"method":[153],"bounds":[155],"total":[156],"class":[157],"exemplars":[158],"through":[159],"unified":[161],"exemplar":[162],"hardware-efficient":[166],"merging":[168],"strategy,":[169],"while":[170],"integrating":[171,202],"quantized":[173],"CNN":[174],"front-end":[175],"reduce":[177],"overhead":[180],"sacrificing":[182],"accuracy.":[183],"system":[186],"realized":[190],"as":[191,254],"dataflow":[194],"architecture":[195],"AMD":[198],"Zynq":[199],"ZCU104":[200],"FPGA,":[201],"hyperdimensional":[203],"encoding,":[204],"similarity":[205],"search,":[206],"bounded":[208],"management":[210],"using":[211],"word-packed":[212],"binary":[213],"hypervector":[214],"representations":[215],"enable":[217],"massively":[218],"parallel":[219],"bitwise":[220],"operations":[221],"within":[222],"tight":[223],"resource":[225],"budgets.":[226],"Experimental":[227],"results":[228],"CORe50":[231],"dataset":[232],"demonstrate":[233],"up":[234],"40.4\u00d7":[236],"(4.84\u00d7)":[237],"speedups":[238],"383\u00d7":[240],"(105.1\u00d7)":[241],"energy":[242],"efficiency":[243],"gains":[244],"over":[245],"optimized":[246],"CPU":[247],"(GPU)":[248],"baselines,":[249],"establishing":[250],"HDC-enabled":[251],"practical":[256],"foundation":[257],"real-time,":[259],"lifelong":[261],"systems.":[263]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-06-11T00:00:00"}
