{"id":"https://openalex.org/W7138970593","doi":"https://doi.org/10.48550/arxiv.2603.16341","title":"PKINet-v2: Towards Powerful and Efficient Poly-Kernel Remote Sensing Object Detection","display_name":"PKINet-v2: Towards Powerful and Efficient Poly-Kernel Remote Sensing Object Detection","publication_year":2026,"publication_date":"2026-03-17","ids":{"openalex":"https://openalex.org/W7138970593","doi":"https://doi.org/10.48550/arxiv.2603.16341"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.16341","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16341","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.16341","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125621091","display_name":"Xinhao Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cai, Xinhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014945486","display_name":"Liulei Li","orcid":"https://orcid.org/0000-0002-4637-0328"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Liulei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082756213","display_name":"Gensheng Pei","orcid":"https://orcid.org/0000-0002-7677-7487"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pei, Gensheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073755558","display_name":"Zeren Sun","orcid":"https://orcid.org/0000-0001-6262-5338"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Zeren","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027545344","display_name":"Yazhou Yao","orcid":"https://orcid.org/0000-0002-0337-9410"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Yazhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130110940","display_name":"Wenguan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wenguan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5125621091"],"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/T10036","display_name":"Advanced Neural Network Applications","score":0.6845999956130981,"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":0.6845999956130981,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.16249999403953552,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.023800000548362732,"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/kernel","display_name":"Kernel (algebra)","score":0.6800000071525574},{"id":"https://openalex.org/keywords/isotropy","display_name":"Isotropy","score":0.5856000185012817},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5285000205039978},{"id":"https://openalex.org/keywords/spatial-coherence","display_name":"Spatial coherence","score":0.527400016784668},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5026999711990356},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.49959999322891235},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.45989999175071716},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4108999967575073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7060999870300293},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6800000071525574},{"id":"https://openalex.org/C184050105","wikidata":"https://www.wikidata.org/wiki/Q273163","display_name":"Isotropy","level":2,"score":0.5856000185012817},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5285000205039978},{"id":"https://openalex.org/C2985909886","wikidata":"https://www.wikidata.org/wiki/Q193147","display_name":"Spatial coherence","level":3,"score":0.527400016784668},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5026999711990356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5016999840736389},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.49959999322891235},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4722000062465668},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.4004000127315521},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3614000082015991},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3343999981880188},{"id":"https://openalex.org/C85725439","wikidata":"https://www.wikidata.org/wiki/Q466686","display_name":"Anisotropy","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2962999939918518},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C124851039","wikidata":"https://www.wikidata.org/wiki/Q2665459","display_name":"Compressed sensing","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.26499998569488525},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.16341","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16341","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.16341","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16341","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":false,"raw_source_name":null,"raw_type":"article"},"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":{"Object":[0],"detection":[1],"in":[2,219],"remote":[3,216],"sensing":[4,217],"images":[5],"(RSIs)":[6],"is":[7],"challenged":[8],"by":[9,44,54],"the":[10,39,71],"coexistence":[11],"of":[12,29],"geometric":[13,95],"and":[14,81,94,106,110,138,197,222],"spatial":[15,76],"complexity:":[16],"targets":[17,52],"may":[18],"appear":[19],"with":[20,134],"diverse":[21],"aspect":[22],"ratios,":[23],"while":[24,148,205],"spanning":[25],"a":[26,108,119,140,162,174,207],"wide":[27],"range":[28],"object":[30],"sizes":[31],"under":[32],"varied":[33],"contexts.":[34],"Existing":[35],"RSI":[36],"backbones":[37,218],"address":[38],"two":[40],"challenges":[41,117],"separately,":[42],"either":[43],"adopting":[45],"anisotropic":[46,131],"strip":[47],"kernels":[48,58,88,137],"to":[49,59,68,212],"model":[50],"slender":[51,98],"or":[53],"using":[55],"isotropic":[56,86,135],"large":[57,87],"capture":[60],"broader":[61],"context.":[62],"However,":[63],"such":[64],"isolated":[65],"treatments":[66],"lead":[67],"complementary":[69],"drawbacks:":[70],"strip-only":[72],"design":[73],"can":[74],"disrupt":[75],"coherence":[77],"for":[78,97,178],"regular-shaped":[79],"objects":[80],"weaken":[82],"tiny":[83],"details,":[84],"whereas":[85],"often":[89],"introduce":[90,161],"severe":[91],"background":[92],"noise":[93],"mismatch":[96],"structures.":[99],"In":[100],"this":[101],"paper,":[102],"we":[103,159],"extend":[104],"PKINet,":[105],"present":[107],"powerful":[109],"efficient":[111,157],"backbone":[112],"that":[113,168,200],"jointly":[114],"handles":[115],"both":[116,220],"within":[118],"unified":[120],"paradigm":[121],"named":[122],"Poly":[123],"Kernel":[124,164],"Inception":[125],"Network":[126],"v2":[127],"(PKINet-v2).":[128],"PKINet-v2":[129,201],"synergizes":[130],"axial-strip":[132],"convolutions":[133],"square":[136],"builds":[139],"multi-scope":[141],"receptive":[142],"field,":[143],"preserving":[144],"fine-grained":[145],"local":[146],"textures":[147],"progressively":[149],"aggregating":[150],"long-range":[151],"context":[152],"across":[153],"scales.":[154],"To":[155],"enable":[156],"deployment,":[158],"further":[160],"Heterogeneous":[163],"Re-parameterization":[165],"(HKR)":[166],"Strategy":[167],"fuses":[169],"all":[170],"heterogeneous":[171],"branches":[172],"into":[173],"single":[175],"depth-wise":[176],"convolution":[177],"inference,":[179],"eliminating":[180],"fragmented":[181],"kernel":[182],"launches":[183],"without":[184],"accuracy":[185,204],"loss.":[186],"Extensive":[187],"experiments":[188],"on":[189],"four":[190],"widely-used":[191],"benchmarks,":[192],"including":[193],"DOTA-v1.0,":[194],"DOTA-v1.5,":[195],"HRSC2016,":[196],"DIOR-R,":[198],"demonstrate":[199],"achieves":[202],"state-of-the-art":[203],"delivering":[206],"$\\textbf{3.9}\\times$":[208],"FPS":[209],"acceleration":[210],"compared":[211],"PKINet-v1,":[213],"surpassing":[214],"previous":[215],"effectiveness":[221],"efficiency.":[223]},"counts_by_year":[],"updated_date":"2026-03-20T20:54:20.808490","created_date":"2026-03-20T00:00:00"}