{"id":"https://openalex.org/W7154361678","doi":"https://doi.org/10.48550/arxiv.2604.10210","title":"A3-FPN: Asymptotic Content-Aware Pyramid Attention Network for Dense Visual Prediction","display_name":"A3-FPN: Asymptotic Content-Aware Pyramid Attention Network for Dense Visual Prediction","publication_year":2026,"publication_date":"2026-04-11","ids":{"openalex":"https://openalex.org/W7154361678","doi":"https://doi.org/10.48550/arxiv.2604.10210"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.10210","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10210","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.2604.10210","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121937118","display_name":"Meng\u2019en Qin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Meng'en","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133615710","display_name":"Yu Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121968548","display_name":"Quanling Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Quanling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133618861","display_name":"Xiaodong Yang","orcid":"https://orcid.org/0009-0006-6931-7438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xiaodong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121912487","display_name":"Yingtao Che","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Che, Yingtao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133624529","display_name":"Xiaohui Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xiaohui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.44920000433921814,"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":0.44920000433921814,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.2313999980688095,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.15369999408721924,"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/discriminative-model","display_name":"Discriminative model","score":0.8066999912261963},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7907000184059143},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.7734000086784363},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6658999919891357},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6398000121116638},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5764999985694885},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5493000149726868},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.49300000071525574},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.451200008392334}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8066999912261963},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7907000184059143},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.7734000086784363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7178999781608582},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6658999919891357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6459000110626221},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6398000121116638},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5764999985694885},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5493000149726868},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.49300000071525574},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3122999966144562},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2903999984264374},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2858000099658966},{"id":"https://openalex.org/C88796919","wikidata":"https://www.wikidata.org/wiki/Q1142907","display_name":"Backbone network","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.27140000462532043},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.10210","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10210","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.2604.10210","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10210","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.795093834400177}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Learning":[0],"multi-scale":[1,52],"representations":[2],"is":[3],"the":[4,56,93],"common":[5],"strategy":[6],"to":[7,50,96,110],"tackle":[8],"object":[9],"scale":[10],"variation":[11,134],"in":[12],"dense":[13],"prediction":[14],"tasks.":[15],"Although":[16],"existing":[17],"feature":[18,53,75,86,115,122,136],"pyramid":[19],"networks":[20],"have":[21],"greatly":[22],"advanced":[23],"visual":[24],"recognition,":[25],"inherent":[26],"design":[27],"defects":[28],"inhibit":[29],"them":[30],"from":[31,81,92],"capturing":[32],"discriminative":[33,121],"features":[34,127],"and":[35,60,77,100,105,124,132,144,156,168,179],"recognizing":[36],"small":[37],"objects.":[38],"In":[39,85,114],"this":[40],"work,":[41],"we":[42],"propose":[43],"Asymptotic":[44],"Content-Aware":[45],"Pyramid":[46],"Attention":[47],"Network":[48],"(A3-FPN),":[49],"augment":[51],"representation":[54],"via":[55],"asymptotically":[57,73],"disentangled":[58],"framework":[59],"content-aware":[61],"attention":[62],"modules.":[63],"Specifically,":[64],"A3-FPN":[65,148,171],"employs":[66],"a":[67],"horizontally-spread":[68],"column":[69],"network":[70],"that":[71,147],"enables":[72],"global":[74],"interaction":[76],"disentangles":[78],"each":[79],"level":[80,95],"all":[82],"hierarchical":[83],"representations.":[84],"fusion,":[87],"it":[88,117],"collects":[89],"supplementary":[90],"content":[91,131],"adjacent":[94],"generate":[97],"position-wise":[98],"offsets":[99],"weights":[101],"for":[102],"context-aware":[103],"resampling,":[104],"learns":[106],"deep":[107],"context":[108],"reweights":[109],"improve":[111],"intra-category":[112],"similarity.":[113],"reassembly,":[116],"further":[118],"strengthens":[119],"intra-scale":[120],"learning":[123],"reassembles":[125],"redundant":[126],"based":[128],"on":[129,140,176,182],"information":[130],"spatial":[133],"of":[135],"maps.":[137],"Extensive":[138],"experiments":[139],"MS":[141,177],"COCO,":[142],"VisDrone2019-DET":[143],"Cityscapes":[145],"demonstrate":[146],"can":[149],"be":[150],"easily":[151],"integrated":[152],"into":[153],"state-of-the-art":[154],"CNN":[155],"Transformer-based":[157],"architectures,":[158],"yielding":[159],"remarkable":[160],"performance":[161],"gains.":[162],"Notably,":[163],"when":[164],"paired":[165],"with":[166],"OneFormer":[167],"Swin-L":[169],"backbone,":[170],"achieves":[172],"49.6":[173],"mask":[174],"AP":[175],"COCO":[178],"85.6":[180],"mIoU":[181],"Cityscapes.":[183],"Codes":[184],"are":[185],"available":[186],"at":[187],"https://github.com/mason-ching/A3-FPN.":[188]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-15T00:00:00"}