{"id":"https://openalex.org/W2979130909","doi":"https://doi.org/10.1109/ijcnn.2019.8851922","title":"Efficient and Robust Convolutional Neural Networks via Channel Prioritization and Path Ensemble","display_name":"Efficient and Robust Convolutional Neural Networks via Channel Prioritization and Path Ensemble","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2979130909","doi":"https://doi.org/10.1109/ijcnn.2019.8851922","mag":"2979130909"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8851922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","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/A5061165180","display_name":"Chun-Min Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chun-Min Chang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045851299","display_name":"Chia-Ching Lin","orcid":"https://orcid.org/0000-0003-2779-6486"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Ching Lin","raw_affiliation_strings":["Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044405835","display_name":"Kuan-Ta Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuan-Ta Chen","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061165180"],"corresponding_institution_ids":["https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57480712,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"abs 1502 3167","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998000264167786,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9606000185012817,"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/T14117","display_name":"Integrated Circuits and Semiconductor Failure Analysis","score":0.9560999870300293,"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/computer-science","display_name":"Computer science","score":0.8276150226593018},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.7630420923233032},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7013953924179077},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6989426612854004},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5704911947250366},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5438798069953918},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5141153931617737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5077806115150452},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.48694026470184326},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.4630212187767029},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.45221203565597534},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.4104832410812378},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3453322649002075},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09484916925430298}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8276150226593018},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.7630420923233032},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7013953924179077},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6989426612854004},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5704911947250366},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5438798069953918},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5141153931617737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5077806115150452},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.48694026470184326},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.4630212187767029},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.45221203565597534},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.4104832410812378},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3453322649002075},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09484916925430298},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2019.8851922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1724438581","https://openalex.org/W1836465849","https://openalex.org/W1996901117","https://openalex.org/W2114766824","https://openalex.org/W2119144962","https://openalex.org/W2124379907","https://openalex.org/W2125389748","https://openalex.org/W2167215970","https://openalex.org/W2520760693","https://openalex.org/W2554931888","https://openalex.org/W2589646680","https://openalex.org/W2593245696","https://openalex.org/W2598097916","https://openalex.org/W2605831051","https://openalex.org/W2612445135","https://openalex.org/W2707890836","https://openalex.org/W2739542029","https://openalex.org/W2754084392","https://openalex.org/W2755956102","https://openalex.org/W2765402136","https://openalex.org/W2786054724","https://openalex.org/W2798722023","https://openalex.org/W2810611310","https://openalex.org/W2899090668","https://openalex.org/W2949117887","https://openalex.org/W2950248853","https://openalex.org/W2950967261","https://openalex.org/W2952746978","https://openalex.org/W2962694340","https://openalex.org/W2962710014","https://openalex.org/W2962851801","https://openalex.org/W2962944050","https://openalex.org/W2962965870","https://openalex.org/W2963000224","https://openalex.org/W2964001144","https://openalex.org/W2964062240","https://openalex.org/W2964082701","https://openalex.org/W2964228333","https://openalex.org/W2964299589","https://openalex.org/W4293350742","https://openalex.org/W4297775537","https://openalex.org/W4300081896","https://openalex.org/W4301429599","https://openalex.org/W4302613003","https://openalex.org/W6637373629","https://openalex.org/W6637709462","https://openalex.org/W6638667902","https://openalex.org/W6677103964","https://openalex.org/W6677580257","https://openalex.org/W6678568454","https://openalex.org/W6678583879","https://openalex.org/W6684563725","https://openalex.org/W6725543821","https://openalex.org/W6726275242","https://openalex.org/W6730382033","https://openalex.org/W6733877748","https://openalex.org/W6734062232","https://openalex.org/W6734169003","https://openalex.org/W6735260822","https://openalex.org/W6735796365","https://openalex.org/W6737664043","https://openalex.org/W6739917289","https://openalex.org/W6741753902","https://openalex.org/W6744890726","https://openalex.org/W6746114988","https://openalex.org/W6746484425","https://openalex.org/W6748035112","https://openalex.org/W6752931940","https://openalex.org/W6755737735"],"related_works":["https://openalex.org/W4315697128","https://openalex.org/W4382323155","https://openalex.org/W3205506801","https://openalex.org/W2971502891","https://openalex.org/W4287067436","https://openalex.org/W4280599700","https://openalex.org/W3183570023","https://openalex.org/W3102845713","https://openalex.org/W4323650687","https://openalex.org/W3005814217"],"abstract_inverted_index":{"With":[0],"the":[1,64,81,87,90,103],"growing":[2],"recognition":[3],"of":[4,83,89],"both":[5],"efficiency":[6],"and":[7,27,40,70,110,134,167,175],"security":[8],"issues":[9],"in":[10,66,140,142],"machine":[11],"learning":[12],"models,":[13],"we":[14,125],"propose":[15],"a":[16,67,106,111,120],"novel":[17],"convolutional":[18],"neural":[19,181],"networks":[20],"(CNNs)":[21],"training":[22],"algorithm,":[23],"called":[24],"channel":[25,84],"prioritization":[26,85],"path":[28],"ensemble":[29,71],"(CPPE),":[30],"to":[31,62,128,178],"not":[32,58],"only":[33,59,119,137],"allow":[34,126],"dynamically":[35,129],"trade-offs":[36,130],"between":[37,131],"different":[38,76],"resource":[39,132],"performance":[41],"requirements":[42],"but":[43],"also":[44],"enable":[45],"secure":[46],"inference":[47,73,151],"without":[48,162],"any":[49,163,179],"extra":[50],"computational":[51,165],"cost":[52,166],"or":[53],"memory":[54,168],"overhead.":[55,169],"Our":[56],"approach":[57],"prioritizes":[60],"channels":[61],"prune":[63],"network":[65,92],"structured":[68],"way":[69],"multiple":[72,150],"paths":[74],"over":[75],"utilization":[77],"conditions.":[78],"We":[79],"demonstrated":[80],"effectiveness":[82],"by":[86],"experiment":[88],"VGG-16":[91],"on":[93,102],"various":[94,159],"benchmark":[95],"datasets.":[96],"The":[97],"experimental":[98],"results":[99],"show":[100],"that,":[101],"CIFAR-10":[104],"dataset,":[105],"10\u00d7":[107],"parameters":[108],"reduction":[109,114],"4\u00d7":[112],"FLOPs":[113,146],"can":[115,155],"be":[116],"achieved,":[117],"with":[118,136],"0.2%":[121],"accuracy":[122,135,141],"drop.":[123],"Furthermore,":[124],"CNNs":[127],"demand":[133],"4%":[138],"degradation":[139],"exchange":[143],"for":[144],"16\u00d7":[145],"reduction.":[147],"By":[148],"ensembling":[149],"paths,":[152],"our":[153,171],"model":[154],"improve":[156],"robustness":[157],"against":[158],"adversarial":[160],"attacks":[161],"additional":[164],"Finally,":[170],"method":[172],"is":[173],"simple":[174],"easily":[176],"applied":[177],"convolutioanl":[180],"networks.":[182]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}