{"id":"https://openalex.org/W3126595748","doi":"https://doi.org/10.1109/tetc.2021.3056031","title":"Fully Dynamic Inference with Deep Neural Networks","display_name":"Fully Dynamic Inference with Deep Neural Networks","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3126595748","doi":"https://doi.org/10.1109/tetc.2021.3056031","mag":"3126595748"},"language":"en","primary_location":{"id":"doi:10.1109/tetc.2021.3056031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2021.3056031","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computing","raw_type":"journal-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/A5066434069","display_name":"Wenhan Xia","orcid":"https://orcid.org/0000-0002-3063-144X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenhan Xia","raw_affiliation_strings":["Department of Electrical Engineering, Princeton University, Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002444694","display_name":"Hongxu Yin","orcid":"https://orcid.org/0000-0002-6481-6389"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongxu Yin","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080137972","display_name":"Xiaoliang Dai","orcid":"https://orcid.org/0000-0003-3098-2714"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoliang Dai","raw_affiliation_strings":["Facebook, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210099336","https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086131079","display_name":"Niraj K. Jha","orcid":"https://orcid.org/0000-0002-1539-0369"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niraj K Jha","raw_affiliation_strings":["Department of Electrical Engineering, Princeton University, Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.621,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.90758074,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9918000102043152,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8487393856048584},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7060409784317017},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5362358093261719},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5298673510551453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5288002490997314},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4722530245780945},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4532027840614319},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4370030462741852},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36806604266166687},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22225308418273926}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8487393856048584},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7060409784317017},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5362358093261719},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5298673510551453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5288002490997314},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4722530245780945},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4532027840614319},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4370030462741852},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36806604266166687},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22225308418273926},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetc.2021.3056031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2021.3056031","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2549139847","https://openalex.org/W2618530766","https://openalex.org/W2739879705","https://openalex.org/W2883780447","https://openalex.org/W2884751099","https://openalex.org/W2887783173","https://openalex.org/W2912984848","https://openalex.org/W2946948417","https://openalex.org/W2962677625","https://openalex.org/W2962935523","https://openalex.org/W2962944050","https://openalex.org/W2963125010","https://openalex.org/W2963145730","https://openalex.org/W2963163009","https://openalex.org/W2963319203","https://openalex.org/W2963844898","https://openalex.org/W2963918968","https://openalex.org/W2964081807","https://openalex.org/W2966225497","https://openalex.org/W2966950562","https://openalex.org/W2980137827","https://openalex.org/W2995785927","https://openalex.org/W3034940165","https://openalex.org/W3034957837","https://openalex.org/W3118608800","https://openalex.org/W3203827521","https://openalex.org/W4246193833","https://openalex.org/W4297775537","https://openalex.org/W6637373629","https://openalex.org/W6637551013","https://openalex.org/W6638523607","https://openalex.org/W6677580257","https://openalex.org/W6679436768","https://openalex.org/W6687566353","https://openalex.org/W6726275242","https://openalex.org/W6729972426","https://openalex.org/W6730047919","https://openalex.org/W6734213132","https://openalex.org/W6737664043","https://openalex.org/W6741753902","https://openalex.org/W6750566404","https://openalex.org/W6755526309","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Modern":[0],"deep":[1,60,130],"neural":[2,61,132],"networks":[3,62,133],"are":[4,63,165],"powerful":[5],"and":[6,33,43,50,89,143,153,167,173,190,210,229,255],"widely":[7],"applicable":[8],"models":[9],"that":[10,102,111,128],"extract":[11],"task-relevant":[12],"information":[13],"through":[14],"multi-level":[15],"abstraction.":[16],"Their":[17],"cross-domain":[18],"success,":[19],"however,":[20],"is":[21],"often":[22],"achieved":[23],"at":[24,138],"the":[25,109,139,214,243,264],"expense":[26],"of":[27,141],"computational":[28,87],"cost,":[29],"high":[30],"memory":[31],"bandwidth,":[32],"long":[34],"inference":[35,49,136,240],"latency,":[36],"which":[37,161],"prevents":[38],"their":[39,65],"deployment":[40,67],"in":[41,219],"resource-constrained":[42],"time-sensitive":[44],"scenarios,":[45],"such":[46],"as":[47],"edge-side":[48],"self-driving":[51],"cars.":[52],"While":[53],"recently":[54],"developed":[55],"methods":[56,96],"for":[57],"creating":[58],"efficient":[59],"making":[64],"real-world":[66],"more":[68],"feasible":[69],"by":[70,108],"reducing":[71],"model":[72],"size,":[73],"they":[74],"do":[75],"not":[76],"fully":[77,125],"exploit":[78],"input":[79],"properties":[80],"on":[81,157],"a":[82,99,124,158,193],"per-instance":[83,159],"basis":[84,160],"to":[85,118,178,183,207,221,231,237,249,257],"maximize":[86,184],"efficiency":[88,209],"task":[90,185],"accuracy.":[91,186,212],"In":[92],"particular,":[93],"most":[94],"existing":[95],"typically":[97],"use":[98],"one-size-fits-all":[100],"approach":[101],"identically":[103],"processes":[104],"all":[105],"inputs.":[106],"Motivated":[107],"fact":[110],"different":[112,115],"images":[113],"require":[114],"feature":[116],"embeddings":[117],"be":[119,170],"accurately":[120],"classified,":[121],"we":[122,199],"propose":[123],"dynamic":[126,203,239],"paradigm":[127],"imparts":[129],"convolutional":[131,145],"with":[134,205],"hierarchical":[135],"dynamics":[137],"level":[140],"layers":[142,162],"individual":[144],"filters/channels.":[146],"Two":[147],"compact":[148],"networks,":[149],"called":[150,197],"Layer-Net":[151],"(L-Net)":[152],"Channel-Net":[154],"(C-Net),":[155],"predict":[156],"or":[163],"filters/channels":[164],"redundant":[166],"therefore":[168],"should":[169],"skipped.":[171],"L-Net":[172,189],"C-Net":[174,191],"also":[175],"learn":[176],"how":[177],"scale":[179],"retained":[180],"computation":[181],"outputs":[182],"By":[187],"integrating":[188],"into":[192],"joint":[194],"design":[195],"framework,":[196],"LC-Net,":[198],"consistently":[200],"outperform":[201],"state-of-the-art":[202],"frameworks":[204],"respect":[206],"both":[208],"classification":[211],"On":[213,242],"CIFAR-10":[215],"dataset,":[216,245],"LC-Net":[217,246],"results":[218],"up":[220,230,248,256],"<inline-formula><tex-math":[222,250],"notation=\"LaTeX\">$11.9\\times$</tex-math><alternatives><mml:math><mml:mrow><mml:mn>11</mml:mn><mml:mo>.</mml:mo><mml:mn>9</mml:mn><mml:mo>&#x00D7;</mml:mo></mml:mrow></mml:math><inline-graphic":[223],"xlink:href=\"xia-ieq1-3056031.gif\"/></alternatives></inline-formula>":[224],"fewer":[225,253],"floating-point":[226],"operations":[227],"(FLOPs)":[228],"3.3":[232],"percent":[233,259],"higher":[234,260],"accuracy":[235,262],"compared":[236],"other":[238,265],"methods.":[241,266],"ImageNet":[244],"achieves":[247],"notation=\"LaTeX\">$1.4\\times$</tex-math><alternatives><mml:math><mml:mrow><mml:mn>1</mml:mn><mml:mo>.</mml:mo><mml:mn>4</mml:mn><mml:mo>&#x00D7;</mml:mo></mml:mrow></mml:math><inline-graphic":[251],"xlink:href=\"xia-ieq2-3056031.gif\"/></alternatives></inline-formula>":[252],"FLOPs":[254],"4.6":[258],"Top-1":[261],"than":[263]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}