{"id":"https://openalex.org/W7147179974","doi":"https://doi.org/10.48550/arxiv.2603.27661","title":"Amped: Adaptive Multi-stage Non-edge Pruning for Edge Detection","display_name":"Amped: Adaptive Multi-stage Non-edge Pruning for Edge Detection","publication_year":2026,"publication_date":"2026-03-29","ids":{"openalex":"https://openalex.org/W7147179974","doi":"https://doi.org/10.48550/arxiv.2603.27661"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.27661","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.27661","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.27661","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132589568","display_name":"Yuhan Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Yuhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132660488","display_name":"Xinqing Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xinqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132624483","display_name":"Xin He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132546345","display_name":"Bing Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Bing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132604099","display_name":"Xinzhong Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Xinzhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132602122","display_name":"Ming-Ming Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Ming-Ming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132649730","display_name":"Yun Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yun","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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.30709999799728394,"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"}},"topics":[{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.30709999799728394,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.1875,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.11010000109672546,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.7631999850273132},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5625},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.541100025177002},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4982999861240387},{"id":"https://openalex.org/keywords/edge-detection","display_name":"Edge detection","score":0.4927999973297119},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.4474000036716461},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.41920000314712524},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.4023999869823456}],"concepts":[{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.7631999850273132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7457000017166138},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5625},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.541100025177002},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4982999861240387},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.4927999973297119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4684999883174896},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.4474000036716461},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.4023999869823456},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.398499995470047},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3910999894142151},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.32409998774528503},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3156999945640564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3089999854564667},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30169999599456787},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.28690001368522644},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26820001006126404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.27661","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.27661","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.27661","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.27661","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Edge":[0,71,131],"detection":[1,112],"is":[2],"a":[3,123,146,160,173],"fundamental":[4],"image":[5],"analysis":[6],"task":[7],"that":[8],"underpins":[9],"numerous":[10],"high-level":[11],"vision":[12],"applications.":[13],"Recent":[14],"advances":[15],"in":[16,163],"Transformer":[17],"architectures":[18],"have":[19],"significantly":[20],"improved":[21],"edge":[22,60,111],"quality":[23],"by":[24,154],"capturing":[25],"long-range":[26],"dependencies,":[27],"but":[28],"this":[29],"often":[30],"comes":[31],"with":[32,99,158],"computational":[33,45],"overhead.":[34],"Achieving":[35],"higher":[36],"pixel-level":[37],"accuracy":[38,92,150],"requires":[39],"increased":[40],"input":[41],"resolution,":[42],"further":[43],"escalating":[44],"cost":[46],"and":[47,78,96,114,138,151],"limiting":[48],"practical":[49],"deployment.":[50],"Building":[51],"on":[52],"the":[53,106,141],"strong":[54],"representational":[55],"capacity":[56],"of":[57,109,177],"recent":[58],"Transformer-based":[59,127],"detectors,":[61],"we":[62,121],"propose":[63],"an":[64],"Adaptive":[65],"Multi-stage":[66],"non-edge":[67,76],"Pruning":[68],"framework":[69],"for":[70],"Detection(Amped).":[72],"Amped":[73],"identifies":[74],"high-confidence":[75],"tokens":[77],"removes":[79],"them":[80],"as":[81,83],"early":[82],"possible":[84],"to":[85,104,134,156],"substantially":[86],"reduce":[87],"computation,":[88],"thus":[89],"retaining":[90],"high":[91],"while":[93],"cutting":[94],"GFLOPs":[95,153],"accelerating":[97],"inference":[98],"minimal":[100],"performance":[101],"loss.":[102],"Moreover,":[103],"mitigate":[105],"structural":[107],"complexity":[108],"existing":[110,136],"networks":[113],"facilitate":[115],"their":[116],"integration":[117],"into":[118],"real-world":[119],"systems,":[120],"introduce":[122],"simple":[124],"yet":[125],"high-performance":[126],"model,":[128],"termed":[129],"Streamline":[130],"Detector(SED).":[132],"Applied":[133],"both":[135],"detectors":[137],"our":[139],"SED,":[140],"proposed":[142],"pruning":[143],"strategy":[144],"provides":[145],"favorable":[147],"balance":[148],"between":[149],"efficiency-reducing":[152],"up":[155],"40%":[157],"only":[159],"0.4%":[161],"drop":[162],"ODS":[164,175],"F-measure.":[165],"In":[166],"addition,":[167],"despite":[168],"its":[169],"simplicity,":[170],"SED":[171],"achieves":[172],"state-of-the-art":[174],"F-measure":[176],"86.5%.":[178],"The":[179],"code":[180],"will":[181],"be":[182],"released.":[183]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-02T00:00:00"}