{"id":"https://openalex.org/W4308075507","doi":"https://doi.org/10.1109/sips55645.2022.9919204","title":"Accelerator Design and Exploration for Deformable Convolution Networks","display_name":"Accelerator Design and Exploration for Deformable Convolution Networks","publication_year":2022,"publication_date":"2022-11-02","ids":{"openalex":"https://openalex.org/W4308075507","doi":"https://doi.org/10.1109/sips55645.2022.9919204"},"language":"en","primary_location":{"id":"doi:10.1109/sips55645.2022.9919204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips55645.2022.9919204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Workshop on Signal Processing Systems (SiPS)","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/A5050528589","display_name":"Yuan Meng","orcid":"https://orcid.org/0000-0001-6468-8623"},"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":true,"raw_author_name":"Yuan Meng","raw_affiliation_strings":["University of Southern California,Ming Hsieh Department of Electrical and Computer Engineering","Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Ming Hsieh Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057029119","display_name":"Hongjiang Men","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":"Hongjiang Men","raw_affiliation_strings":["University of Southern California,Ming Hsieh Department of Electrical and Computer Engineering","Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Ming Hsieh Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113655787","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,Ming Hsieh Department of Electrical and Computer Engineering","Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Ming Hsieh Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050528589"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.302,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.54760618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9955999851226807,"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":0.994700014591217,"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":0.8754435181617737},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7398873567581177},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7048749923706055},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.6279079914093018},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6112214922904968},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.5232040882110596},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.500798225402832},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4831085205078125},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4763872027397156},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.45825377106666565},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.43499237298965454},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.429007887840271},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3860301971435547},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10944309830665588},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10520040988922119},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09703058004379272},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.0853031575679779}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8754435181617737},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7398873567581177},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7048749923706055},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.6279079914093018},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6112214922904968},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.5232040882110596},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.500798225402832},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4831085205078125},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4763872027397156},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.45825377106666565},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.43499237298965454},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.429007887840271},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3860301971435547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10944309830665588},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10520040988922119},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09703058004379272},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0853031575679779},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sips55645.2022.9919204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips55645.2022.9919204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Workshop on Signal Processing Systems (SiPS)","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":19,"referenced_works":["https://openalex.org/W1977803706","https://openalex.org/W2342840547","https://openalex.org/W2601564443","https://openalex.org/W2899915146","https://openalex.org/W2900082550","https://openalex.org/W2966926453","https://openalex.org/W3038678488","https://openalex.org/W3089673885","https://openalex.org/W3091969046","https://openalex.org/W3110305433","https://openalex.org/W3111051040","https://openalex.org/W3112948415","https://openalex.org/W3129894558","https://openalex.org/W3132460984","https://openalex.org/W3149284388","https://openalex.org/W3213510604","https://openalex.org/W4206902753","https://openalex.org/W6704559304","https://openalex.org/W6789320085"],"related_works":["https://openalex.org/W4313341326","https://openalex.org/W2518118925","https://openalex.org/W3035662153","https://openalex.org/W3159273459","https://openalex.org/W3133116121","https://openalex.org/W2625058759","https://openalex.org/W3193212547","https://openalex.org/W3032310658","https://openalex.org/W3157864596","https://openalex.org/W2971009090"],"abstract_inverted_index":{"Deformable":[0,105],"Convolution":[1],"Network":[2],"(DCN)":[3],"is":[4],"a":[5,27,97],"special":[6],"type":[7],"of":[8,54],"CNN":[9],"that":[10],"achieves":[11,111],"superior":[12],"detection":[13],"accuracy.":[14],"DCN":[15,29],"has":[16],"input-dependent":[17],"dynamic":[18],"data":[19,46,65,77],"access":[20,70,78],"patterns.":[21],"In":[22],"this":[23],"work,":[24],"we":[25],"propose":[26,83],"hybrid":[28,94],"accelerator":[30],"design.":[31],"It":[32],"exploits":[33],"both":[34],"hardware":[35,38],"re-use":[36,51],"and":[37,107,125],"pipelining":[39,44],"on":[40,96],"an":[41,84],"FPGA.":[42],"Hardware":[43,50],"overlaps":[45],"communication":[47],"with":[48,120,136],"computation.":[49],"ensures":[52],"scalability":[53],"the":[55,69,76,121],"design":[56,86,103,110],"to":[57,67,72,91,113,127],"very":[58],"deep":[59],"networks.":[60],"We":[61,82,100],"adopt":[62],"channel-major":[63],"order":[64],"layout":[66],"reduce":[68],"time":[71],"DRAM;":[73],"This":[74],"hides":[75],"overheads":[79],"in":[80,131],"DCNs.":[81],"efficient":[85],"space":[87],"exploration":[88],"(DSE)":[89],"heuristic":[90],"generate":[92],"optimized":[93],"accelerators":[95,139],"given":[98],"device.":[99],"implement":[101],"our":[102],"targeting":[104],"ResNet-50":[106],"ResNet-101.":[108],"Our":[109],"up":[112,126],"24.7":[114],"(2.4)":[115],"times":[116,129],"higher":[117],"throughput":[118],"compared":[119,135],"CPU":[122],"(GPU)":[123],"baselines,":[124],"4.5":[128],"improvement":[130],"effective":[132],"resource":[133],"utilization":[134],"state-of-the-art":[137],"FPGA":[138],"for":[140],"DCN.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}