{"id":"https://openalex.org/W4414856521","doi":"https://doi.org/10.1109/tgrs.2025.3618293","title":"SAFF-DETR: An End-to-End Object Detection Network for Remote Sensing Images With Targets of Varying Sizes Based on Scale Adaptation and Frequency Fusion","display_name":"SAFF-DETR: An End-to-End Object Detection Network for Remote Sensing Images With Targets of Varying Sizes Based on Scale Adaptation and Frequency Fusion","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414856521","doi":"https://doi.org/10.1109/tgrs.2025.3618293"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2025.3618293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3618293","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Geoscience and Remote Sensing","raw_type":"journal-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/A5071040769","display_name":"Yuanjie Zhi","orcid":"https://orcid.org/0000-0001-9883-5353"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuanjie Zhi","raw_affiliation_strings":["School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianglin Zhao","orcid":"https://orcid.org/0009-0009-2242-9389"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianglin Zhao","raw_affiliation_strings":["School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025021168","display_name":"Chao Song","orcid":"https://orcid.org/0000-0002-7695-7904"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Song","raw_affiliation_strings":["School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046390538","display_name":"Mingyang Ma","orcid":"https://orcid.org/0000-0002-2944-628X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyang Ma","raw_affiliation_strings":["School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067207818","display_name":"Shaohui Mei","orcid":"https://orcid.org/0000-0002-8018-596X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohui Mei","raw_affiliation_strings":["School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5071040769"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":1.0862,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84084972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"63","issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9959999918937683,"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"}},"topics":[{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9959999918937683,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.98580002784729,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.980400025844574,"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/object-detection","display_name":"Object detection","score":0.6560999751091003},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.4839000105857849},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4661000072956085},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44209998846054077},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4374000132083893},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.4101000130176544},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.39959999918937683},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.39910000562667847},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.38679999113082886}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062000274658203},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6560999751091003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5594000220298767},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4661000072956085},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44209998846054077},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.42669999599456787},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4187999963760376},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.4101000130176544},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.37310001254081726},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.2867000102996826},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C183365957","wikidata":"https://www.wikidata.org/wiki/Q17140402","display_name":"Remote sensing application","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2531000077724457},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2517000138759613},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.2513999938964844},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2025.3618293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3618293","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Geoscience and Remote Sensing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3343969587","display_name":null,"funder_award_id":"62201445","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7086408190","display_name":null,"funder_award_id":"62006193","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W2005368619","https://openalex.org/W2077423447","https://openalex.org/W2176924101","https://openalex.org/W2533214323","https://openalex.org/W2565639579","https://openalex.org/W2577537809","https://openalex.org/W2612624696","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963857746","https://openalex.org/W3011688396","https://openalex.org/W3021258337","https://openalex.org/W3035178397","https://openalex.org/W3092663126","https://openalex.org/W3096609285","https://openalex.org/W3107032263","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3138958001","https://openalex.org/W3168888670","https://openalex.org/W3199093552","https://openalex.org/W3209002923","https://openalex.org/W4214507171","https://openalex.org/W4214627427","https://openalex.org/W4224903303","https://openalex.org/W4242321689","https://openalex.org/W4280563105","https://openalex.org/W4312312588","https://openalex.org/W4312692509","https://openalex.org/W4361274151","https://openalex.org/W4385245566","https://openalex.org/W4386065740","https://openalex.org/W4386083115","https://openalex.org/W4387879465","https://openalex.org/W4388642328","https://openalex.org/W4390871672","https://openalex.org/W4390871882","https://openalex.org/W4390873750","https://openalex.org/W4391130239","https://openalex.org/W4391307079","https://openalex.org/W4391559729","https://openalex.org/W4394711454","https://openalex.org/W4400728888","https://openalex.org/W4402754006","https://openalex.org/W4404582922","https://openalex.org/W4405440087","https://openalex.org/W4407625892","https://openalex.org/W4407736715"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"learning-based":[1],"object":[2,48,191],"detection":[3,49],"algorithms":[4,31],"have":[5],"achieved":[6],"significant":[7],"success":[8],"in":[9,22,84,169],"the":[10,16,88,110,139,150,155,201],"field":[11],"of":[12,19,35,76,144],"computer":[13],"vision.":[14],"However,":[15],"wide":[17],"range":[18],"target":[20],"sizes":[21,37,78],"remote":[23,52],"sensing":[24,53],"images":[25,54],"poses":[26],"a":[27,66,80,95],"challenge":[28],"for":[29,51,142,190],"single":[30,81],"to":[32,73,86,92,103,113,129,164,186],"detect":[33],"objects":[34],"varying":[36,77],"effectively.":[38],"To":[39],"address":[40],"this":[41,43],"issue,":[42],"paper":[44],"proposes":[45],"an":[46],"end-to-end":[47],"algorithm":[50],"based":[55],"on":[56],"Scale":[57],"Adaptive":[58],"and":[59,70,120,125,175,209],"Frequency":[60,122,158],"Fusion":[61,159],"DETR":[62],"(SAFF-DETR),":[63],"which":[64,179],"designs":[65],"frequency":[67,107,132],"feature":[68,133,167],"enhancement":[69],"fusion":[71,98],"mechanism":[72],"handle":[74,205],"targets":[75,143,208],"within":[79],"framework.":[82],"First,":[83],"order":[85],"improve":[87],"Transformer-based":[89],"detectors\u2019":[90],"ability":[91,112],"small":[93,115],"targets,":[94],"multibranch":[96],"representation":[97,140],"(MRF)":[99],"module":[100],"is":[101,127,162,184],"proposed":[102,202],"fuse":[104],"shallow":[105],"layer":[106],"representations,":[108],"boosting":[109],"network\u2019s":[111],"perceive":[114],"targets.":[116],"Furthermore,":[117],"Cross-layer":[118,156],"Spatial":[119],"Channel":[121],"Attention":[123],"(CSFA":[124],"CCFA)":[126],"designed":[128,185],"enable":[130],"efficient":[131],"interaction":[134],"across":[135],"multi-scale":[136],"features,":[137],"enhancing":[138],"capability":[141],"different":[145],"sizes.":[146],"Moreover,":[147],"by":[148,178],"integrating":[149],"two":[151],"aforementioned":[152],"attention":[153],"mechanisms,":[154],"Channel-Spatial-wise":[157],"(CCSFF)":[160],"structure":[161],"introduced":[163],"realize":[165],"global":[166],"interactions":[168],"one":[170],"step":[171],"without":[172],"repetitive":[173],"up":[174],"down-sampling":[176],"operations,":[177],"patch":[180],"division-based":[181],"Transformer":[182],"architecture":[183],"enhance":[187],"scale":[188],"adaptability":[189],"detection.":[192],"Experimental":[193],"results":[194],"over":[195],"several":[196,211],"benchmark":[197],"datasets":[198],"demonstrate":[199],"that":[200],"SAFF-DETR":[203],"can":[204],"extremely":[206],"varying-size":[207],"outperforms":[210],"SOTA":[212],"algorithms.":[213],"The":[214],"source":[215],"code":[216],"will":[217],"be":[218],"available":[219],"at":[220],"https://github.com/Jianglin-Zhao/SAFF-DETR.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}