{"id":"https://openalex.org/W3175556986","doi":"https://doi.org/10.1109/aicas51828.2021.9458472","title":"A Quality-Oriented Reconfigurable Convolution Engine Using Cross-Shaped Sparse Kernels for Highly-Parallel CNN Acceleration","display_name":"A Quality-Oriented Reconfigurable Convolution Engine Using Cross-Shaped Sparse Kernels for Highly-Parallel CNN Acceleration","publication_year":2021,"publication_date":"2021-06-06","ids":{"openalex":"https://openalex.org/W3175556986","doi":"https://doi.org/10.1109/aicas51828.2021.9458472","mag":"3175556986"},"language":"en","primary_location":{"id":"doi:10.1109/aicas51828.2021.9458472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aicas51828.2021.9458472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems (AICAS)","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/A5041190562","display_name":"Chi-Wen Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chi-Wen Weng","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042036635","display_name":"Chao-Tsung Huang","orcid":"https://orcid.org/0000-0002-9173-520X"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chao-Tsung Huang","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":0.191,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.48693708,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","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/T11105","display_name":"Advanced Image Processing Techniques","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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9997000098228455,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/reconfigurability","display_name":"Reconfigurability","score":0.805128276348114},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7656323909759521},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7309130430221558},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.6592710614204407},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6130704879760742},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.5970644950866699},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.5429536700248718},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5410569310188293},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5128819942474365},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.4604834020137787},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.433544397354126},{"id":"https://openalex.org/keywords/peak-signal-to-noise-ratio","display_name":"Peak signal-to-noise ratio","score":0.41053956747055054},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.40001970529556274},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3818609118461609},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31743741035461426},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.27489662170410156},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12359863519668579}],"concepts":[{"id":"https://openalex.org/C2780149590","wikidata":"https://www.wikidata.org/wiki/Q7302742","display_name":"Reconfigurability","level":2,"score":0.805128276348114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7656323909759521},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7309130430221558},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6592710614204407},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6130704879760742},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.5970644950866699},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.5429536700248718},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5410569310188293},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5128819942474365},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.4604834020137787},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.433544397354126},{"id":"https://openalex.org/C154579607","wikidata":"https://www.wikidata.org/wiki/Q3373850","display_name":"Peak signal-to-noise ratio","level":3,"score":0.41053956747055054},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40001970529556274},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3818609118461609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31743741035461426},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27489662170410156},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12359863519668579},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aicas51828.2021.9458472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aicas51828.2021.9458472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems (AICAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.7200000286102295}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322108","display_name":"Ministry of Science and Technology","ror":"https://ror.org/032e49973"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2119144962","https://openalex.org/W2242218935","https://openalex.org/W2279098554","https://openalex.org/W2508457857","https://openalex.org/W2612445135","https://openalex.org/W2625457103","https://openalex.org/W2764207251","https://openalex.org/W2963372104","https://openalex.org/W2963470893","https://openalex.org/W2964299589","https://openalex.org/W2979439447","https://openalex.org/W2979590285","https://openalex.org/W3015478592","https://openalex.org/W3102659484","https://openalex.org/W3104725225","https://openalex.org/W4297775537","https://openalex.org/W6677580257","https://openalex.org/W6695314431","https://openalex.org/W6737664043","https://openalex.org/W6768774720"],"related_works":["https://openalex.org/W1544665014","https://openalex.org/W2748364266","https://openalex.org/W4243861219","https://openalex.org/W2556374054","https://openalex.org/W2069545207","https://openalex.org/W2092579166","https://openalex.org/W2969723039","https://openalex.org/W1977947048","https://openalex.org/W2914540329","https://openalex.org/W2045818635"],"abstract_inverted_index":{"Computational":[0],"imaging":[1],"CNNs":[2],"are":[3],"computationally":[4],"intensive":[5],"and":[6,41,78,101,142,148,168],"need":[7],"complexity":[8,60,117],"reduction":[9,18],"to":[10,20,56,82,94,181],"support":[11,95],"high-throughput":[12],"applications.":[13],"However,":[14],"conventional":[15],"compact":[16,83],"model":[17,59],"tends":[19],"degrade":[21],"image":[22,63],"quality":[23,64],"severely":[24],"as":[25],"models":[26],"become":[27],"too":[28],"shallow.":[29],"On":[30],"the":[31,128,154],"other":[32],"hand,":[33],"irregular":[34],"pruning-based":[35],"techniques":[36],"induce":[37],"considerable":[38],"circuit":[39],"overheads":[40,147],"imbalanced":[42],"workloads,":[43],"especially":[44],"for":[45,105,114,135,153,165],"highly-parallel":[46,90],"accelerators.":[47],"In":[48],"this":[49,169],"paper,":[50],"we":[51,87,158],"propose":[52],"cross-shaped":[53],"sparse":[54],"kernels":[55],"regularly":[57],"reduce":[58],"while":[61],"preserving":[62],"well.":[65],"They":[66],"improve":[67],"PSNR":[68],"(peak":[69],"signal-to-noise":[70],"ratio)":[71],"by":[72],"0.03-0.31":[73],"dB":[74],"on":[75,163],"classic":[76],"denoising":[77],"super-resolution":[79],"networks":[80],"compared":[81],"depth":[84],"reduction.":[85],"Moreover,":[86],"design":[88],"a":[89,115,160],"reconfigurable":[91],"convolution":[92],"engine":[93,129],"three":[96],"sparsity":[97],"configurations":[98],"(0%,":[99],"50%":[100],"75%":[102],"of":[103,122,132,139,179],"sparsity)":[104],"our":[106],"complexity-saving":[107],"method.":[108],"It":[109],"can":[110,171],"achieve":[111,172],"high-quality":[112],"inference":[113,140],"wide":[116],"range":[118],"with":[119],"full":[120],"utilization":[121],"MACs.":[123],"With":[124],"TSMC":[125],"40nm":[126],"technology,":[127],"uses":[130],"9.85M":[131],"logic":[133,146],"gates":[134],"delivering":[136],"8.2":[137],"TOPS":[138],"capability,":[141],"only":[143],"needs":[144],"8.4%":[145],"14.9%":[149],"additional":[150],"power":[151],"consumption":[152],"quality-oriented":[155],"reconfigurability.":[156],"Finally,":[157],"do":[159],"case":[161],"study":[162],"ERNets":[164],"real-time":[166],"inference,":[167],"work":[170],"10.114.8x":[173],"higher":[174],"area":[175],"efficiency":[176],"in":[177],"terms":[178],"Mpixel/s/mm2compared":[180],"SparTen.":[182]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}