{"id":"https://openalex.org/W7133844883","doi":"https://doi.org/10.48550/arxiv.2603.03598","title":"ARMOR: Robust and Efficient CNN-Based SAR ATR through Model-Hardware Co-Design","display_name":"ARMOR: Robust and Efficient CNN-Based SAR ATR through Model-Hardware Co-Design","publication_year":2026,"publication_date":"2026-03-04","ids":{"openalex":"https://openalex.org/W7133844883","doi":"https://doi.org/10.48550/arxiv.2603.03598"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.03598","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128188472","display_name":"Sachini Wickramasinghe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wickramasinghe, Sachini","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128139640","display_name":"Tian Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061917121","display_name":"Cauligi S. Raghavendra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raghavendra, Cauligi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128164640","display_name":"Viktor Prasanna","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prasanna, Viktor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.7595000267028809,"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":0.7595000267028809,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.1242000013589859,"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/T11038","display_name":"Advanced SAR Imaging Techniques","score":0.05249999836087227,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/robustness","display_name":"Robustness (evolution)","score":0.7560999989509583},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7218999862670898},{"id":"https://openalex.org/keywords/synthetic-aperture-radar","display_name":"Synthetic aperture radar","score":0.6531999707221985},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5928000211715698},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.541700005531311},{"id":"https://openalex.org/keywords/automatic-target-recognition","display_name":"Automatic target recognition","score":0.5080000162124634},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4510999917984009},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.40720000863075256}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8113999962806702},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7560999989509583},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7218999862670898},{"id":"https://openalex.org/C87360688","wikidata":"https://www.wikidata.org/wiki/Q740686","display_name":"Synthetic aperture radar","level":2,"score":0.6531999707221985},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5928000211715698},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.541700005531311},{"id":"https://openalex.org/C117623542","wikidata":"https://www.wikidata.org/wiki/Q621974","display_name":"Automatic target recognition","level":3,"score":0.5080000162124634},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4510999917984009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42160001397132874},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.39089998602867126},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3677999973297119},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3666999936103821},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34940001368522644},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3239000141620636},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.3027999997138977},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C203864433","wikidata":"https://www.wikidata.org/wiki/Q5426992","display_name":"FPGA prototype","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.03598","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.03598","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.03598","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2603.03598","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.43096664547920227,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"have":[4],"achieved":[5],"state-of-the-art":[6],"accuracy":[7],"in":[8,50],"Synthetic":[9],"Aperture":[10],"Radar":[11],"(SAR)":[12],"Automatic":[13],"Target":[14],"Recognition":[15],"(ATR).":[16],"However,":[17],"their":[18],"high":[19],"computational":[20],"cost,":[21],"latency,":[22],"and":[23,56,114,156,180,215,238],"memory":[24],"footprint":[25],"make":[26],"its":[27],"deployment":[28],"challenging":[29],"on":[30,112,175,242],"resource-constrained":[31],"platforms":[32],"such":[33],"as":[34],"small":[35],"satellites.":[36],"While":[37],"adversarial":[38,133],"robustness":[39,55,134],"is":[40,47],"critical":[41],"for":[42,78,236],"real-world":[43],"SAR":[44,80,240],"ATR,":[45],"it":[46],"often":[48],"overlooked":[49],"system-level":[51],"optimizations.":[52],"Achieving":[53],"both":[54,152],"inference":[57,213],"efficiency":[58,127,222],"requires":[59],"a":[60,74,99,136],"unified":[61],"framework":[62,77,190,235],"that":[63,82,124,150,188],"considers":[64],"adversarially":[65],"trained":[66],"models":[67,123,169,192],"together":[68],"with":[69,87,144,197],"hardware":[70,100,126],"constraints.":[71],"We":[72,139],"present":[73],"model-hardware":[75],"co-design":[76,234],"CNN-based":[79],"ATR":[81,241],"integrates":[83],"robustness-preserving":[84],"model":[85,102],"compression":[86,92],"FPGA":[88,106,142,172,205,243],"accelerator":[89,143],"design.":[90],"The":[91],"stage":[93],"includes":[94],"hardware-guided":[95],"structured":[96],"pruning,":[97],"where":[98],"performance":[101],"derived":[103],"from":[104],"the":[105,109,119,167,176,229,232],"design":[107,140,162],"predicts":[108],"pruning":[110],"impact":[111],"latency":[113,214],"resource":[115],"usage.":[116],"This":[117],"enables":[118],"generation":[120,163],"of":[121,231],"Pareto-optimal":[122],"improve":[125],"under":[128],"user-defined":[129],"objectives,":[130],"while":[131,201],"maintaining":[132],"within":[135],"predefined":[137],"tolerance.":[138],"an":[141],"channel-aware":[145],"Processing":[146],"Element":[147],"(PE)":[148],"allocation":[149],"supports":[151],"fully":[153],"pipelined":[154],"streaming":[155],"temporal":[157],"resource-reuse":[158],"architectures.":[159],"An":[160],"automated":[161],"flow":[164],"efficiently":[165],"maps":[166],"compressed":[168],"to":[170,194,209,217,224],"optimized":[171],"implementations.":[173],"Experiments":[174],"widely":[177],"used":[178],"MSTAR":[179],"FUSAR-Ship":[181],"datasets":[182],"across":[183],"three":[184],"CNN":[185],"architectures":[186],"show":[187],"our":[189],"produces":[191],"up":[193,208,216],"18.3x":[195],"smaller":[196],"3.1x":[198],"fewer":[199],"MACs":[200],"preserving":[202],"robustness.":[203],"Our":[204],"implementation":[206],"achieves":[207],"68.1x":[210],"(6.4x)":[211],"lower":[212],"169.7x":[218],"(33.2x)":[219],"better":[220],"energy":[221],"compared":[223],"CPU":[225],"(GPU)":[226],"baselines,":[227],"demonstrating":[228],"effectiveness":[230],"proposed":[233],"robust":[237],"efficient":[239],"platforms.":[244]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-06T00:00:00"}