{"id":"https://openalex.org/W4308236831","doi":"https://doi.org/10.1109/icip46576.2022.9897574","title":"Dispense Mode for Inference to Accelerate Branchynet","display_name":"Dispense Mode for Inference to Accelerate Branchynet","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308236831","doi":"https://doi.org/10.1109/icip46576.2022.9897574"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897574","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","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/A5101619210","display_name":"Zhiwei Liang","orcid":"https://orcid.org/0000-0002-6454-5339"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiwei Liang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052528809","display_name":"Yuezhi Zhou","orcid":"https://orcid.org/0000-0002-1850-3007"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuezhi Zhou","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101619210"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.1199,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.42421218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.995199978351593,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/inference","display_name":"Inference","score":0.845710277557373},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7697544693946838},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.6632914543151855},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.6150655150413513},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6006953716278076},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5530786514282227},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5357668995857239},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5322278141975403},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.49654728174209595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.398563027381897},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37222349643707275},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1066669225692749}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.845710277557373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7697544693946838},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.6632914543151855},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.6150655150413513},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6006953716278076},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5530786514282227},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5357668995857239},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5322278141975403},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.49654728174209595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.398563027381897},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37222349643707275},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1066669225692749},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip46576.2022.9897574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897574","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1821462560","https://openalex.org/W2194775991","https://openalex.org/W2567642374","https://openalex.org/W2604319603","https://openalex.org/W2707890836","https://openalex.org/W2950865323","https://openalex.org/W2962677625","https://openalex.org/W2963122961","https://openalex.org/W2966950562","https://openalex.org/W2979679572","https://openalex.org/W3016208860","https://openalex.org/W3049640275","https://openalex.org/W3051231527","https://openalex.org/W3092082681","https://openalex.org/W3102767875","https://openalex.org/W3118608800","https://openalex.org/W4243928383","https://openalex.org/W4288347505","https://openalex.org/W6637373629","https://openalex.org/W6638523607","https://openalex.org/W6739651123","https://openalex.org/W6739917289","https://openalex.org/W6762100871","https://openalex.org/W6763260857","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W2153719181","https://openalex.org/W1971748923","https://openalex.org/W1566155057","https://openalex.org/W2060986072","https://openalex.org/W2052574922","https://openalex.org/W64588465","https://openalex.org/W3120641340","https://openalex.org/W2117825986","https://openalex.org/W3128807919","https://openalex.org/W3176411177"],"abstract_inverted_index":{"With":[0],"the":[1,12,16,34,43,56,60,70,85,92,100,104,107,112,115,122,126,135,161,164],"increase":[2],"of":[3,36,59,89,103,114,138,153,163],"depth":[4],"and":[5,87],"width,":[6],"Deep":[7],"Neural":[8],"Network":[9],"has":[10,23,64],"got":[11],"best":[13],"results":[14],"in":[15,69,106],"computer":[17],"vision,":[18],"but":[19],"its":[20],"massive":[21],"calculation":[22,57],"brought":[24],"a":[25,75,148],"heavy":[26],"burden":[27],"to":[28,54,78,111,166],"IOT":[29],"devices.":[30],"To":[31],"speed":[32,128],"up":[33],"inference":[35,71,127],"DNN":[37],"models,":[38],"Branchynet":[39,63],"creatively":[40],"puts":[41],"forward":[42],"early":[44],"exit,":[45],"which":[46,82],"means":[47],"that":[48],"samples":[49],"exit":[50,101],"from":[51],"shallow":[52],"layers":[53],"reduce":[55],"amount":[58],"model.":[61],"But":[62],"some":[65],"unnecessary":[66],"intermediate":[67,118],"calculations":[68],"process.":[72],"We":[73],"propose":[74],"dispense":[76,96],"mode":[77,97,137],"solve":[79],"this":[80],"problem,":[81],"can":[83,158],"optimize":[84],"accuracy":[86,124,162],"latency":[88],"BranchyNet":[90],"at":[91],"same":[93,123],"time.":[94],"The":[95],"directly":[98],"determines":[99],"position":[102],"sample":[105,116],"multi-branch":[108],"network":[109],"according":[110],"difficulty":[113],"without":[117],"trial":[119],"errors.":[120],"Under":[121],"requirements,":[125],"is":[129],"improved":[130],"by":[131],"30%-50%":[132],"compared":[133],"with":[134],"cascade":[136],"Branchynet.":[139],"Moreover,":[140],"while":[141],"further":[142],"reducing":[143],"redundant":[144],"calculation,":[145],"it":[146],"provides":[147],"method":[149],"for":[150],"dynamic":[151],"adjustment":[152],"accuracy.":[154],"Thus,":[155],"our":[156],"framework":[157],"easily":[159],"adjust":[160],"model":[165],"meet":[167],"higher":[168],"throughputs.":[169]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}