{"id":"https://openalex.org/W7213754151","doi":"https://doi.org/10.20944/preprints202609.0449.v2","title":"Benchmarking Real-Time DETR Detectors for Multibeam Forward-Looking Sonar: DEIMv2, Detector-Specific Test-Time Fusion, and Domain Shift Analysis on UATD","display_name":"Benchmarking Real-Time DETR Detectors for Multibeam Forward-Looking Sonar: DEIMv2, Detector-Specific Test-Time Fusion, and Domain Shift Analysis on UATD","publication_year":2026,"publication_date":"2026-09-20","ids":{"openalex":"https://openalex.org/W7213754151","doi":"https://doi.org/10.20944/preprints202609.0449.v2"},"language":"en","primary_location":{"id":"doi:10.20944/preprints202609.0449.v2","doi":"https://doi.org/10.20944/preprints202609.0449.v2","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202609.0449.v2","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"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":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.20944/preprints202609.0449.v2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5149567867","display_name":"Hao Yuan","orcid":"https://orcid.org/0009-0009-5544-5414","observed_orcids":["https://orcid.org/0009-0009-5544-5414"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Yuan","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0009-5544-5414","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100746929","display_name":"Wenbo Wang","orcid":"https://orcid.org/0000-0002-2130-7672","observed_orcids":["https://orcid.org/0000-0002-2130-7672","https://orcid.org/0000-0002-0911-3189"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wenbo Wang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2130-7672","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150715930","display_name":"Tian Li","orcid":"https://orcid.org/0009-0002-3378-2646","observed_orcids":["https://orcid.org/0009-0002-3378-2646"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Li","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0002-3378-2646","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109490309","display_name":"Lingjiang Zeng","orcid":"https://orcid.org/0009-0001-2488-6657","observed_orcids":["https://orcid.org/0009-0001-2488-6657"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingjiang Zeng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0001-2488-6657","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150716751","display_name":"Yu Chen","orcid":"https://orcid.org/0009-0002-2067-6297","observed_orcids":["https://orcid.org/0009-0002-2067-6297"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Chen","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0002-2067-6297","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108050054","display_name":"Fanyu Wang","orcid":"https://orcid.org/0000-0002-9937-8534","observed_orcids":["https://orcid.org/0000-0002-9937-8534","https://orcid.org/0009-0004-7862-171X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fanyu Wang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0004-7862-171X","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5100746929"],"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/T11698","display_name":"Underwater Acoustics Research","score":0.8852999806404114,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.8852999806404114,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.10140000283718109,"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/T11192","display_name":"Underwater Vehicles and Communication Systems","score":0.0032999999821186066,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/underwater-acoustic-target-detection","display_name":"underwater acoustic target detection","score":0.8569999933242798},{"id":"https://openalex.org/keywords/dinov3","display_name":"DINOv3","score":0.796999990940094},{"id":"https://openalex.org/keywords/weighted-box-fusion","display_name":"weighted box fusion","score":0.8360000252723694},{"id":"https://openalex.org/keywords/domain-shift","display_name":"domain shift","score":0.8859999775886536},{"id":"https://openalex.org/keywords/distribution-shift","display_name":"distribution shift","score":0.7179999947547913},{"id":"https://openalex.org/keywords/real-time-object-detection","display_name":"real-time object detection","score":0.6069999933242798},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.5320000052452087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.631600022315979},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5690000057220459},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5684000253677368},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.531000018119812},{"id":"https://openalex.org/C555745239","wikidata":"https://www.wikidata.org/wiki/Q133220","display_name":"Sonar","level":2,"score":0.4860000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.482699990272522},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.4763000011444092},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4742000102996826},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4699999988079071},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4602000117301941},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.42080000042915344},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C60478076","wikidata":"https://www.wikidata.org/wiki/Q3036835","display_name":"Reference data","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.27869999408721924},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26989999413490295},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25920000672340393},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.20944/preprints202609.0449.v2","doi":"https://doi.org/10.20944/preprints202609.0449.v2","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202609.0449.v2","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"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":"posted-content"}],"best_oa_location":{"id":"doi:10.20944/preprints202609.0449.v2","doi":"https://doi.org/10.20944/preprints202609.0449.v2","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202609.0449.v2","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"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":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7215052542","https://openalex.org/W7211977022","https://openalex.org/W4310742868","https://openalex.org/W4408200400","https://openalex.org/W7150097781","https://openalex.org/W4413869810","https://openalex.org/W7172401408","https://openalex.org/W4409473644","https://openalex.org/W7162423818","https://openalex.org/W7166652235"],"abstract_inverted_index":{"Multibeam":[0],"forward-looking":[1],"sonar":[2],"(MFLS)":[3],"target":[4],"detection":[5],"remains":[6],"challenging":[7],"because":[8],"of":[9,102,122],"low":[10],"spatial":[11],"resolution,":[12,60],"acoustic":[13],"speckle,":[14],"and":[15,52,65,72,78,92,97,104,136,142,156,158,166,182,190,211,237,241],"distributional":[16,206],"differences":[17],"across":[18],"survey":[19],"conditions.":[20],"This":[21],"study":[22,225],"benchmarks":[23],"DEIMv2,":[24],"a":[25,39,55,177,227],"DINOv3-based":[26],"real-time":[27],"DETR-family":[28,232],"detector,":[29],"on":[30,95,140,234],"the":[31,111,123,146,162,200,209,221],"Underwater":[32],"Acoustic":[33],"Target":[34],"Detection":[35],"(UATD)":[36],"dataset":[37,57],"under":[38,54],"specified,":[40],"reproducible":[41,228],"dual-test-split":[42],"protocol.":[43],"We":[44,174],"compare":[45],"DEIMv2":[46],"with":[47,100,204],"RT-DETR-R18,":[48],"D-FINE-S,":[49],"DEIM":[50],"v1-S,":[51],"YOLOv8-S":[53],"common":[56],"split,":[58],"input":[59],"training":[61],"budget,":[62],"augmentation":[63,85],"schedule,":[64],"evaluation":[66],"pipeline,":[67],"while":[68],"retaining":[69],"model-specific":[70],"initialization":[71],"official":[73],"optimization":[74],"details":[75],"(Section":[76],"4.2),":[77],"evaluate":[79],"weighted":[80],"boxes":[81],"fusion":[82,148,244],"(WBF)":[83],"test-time":[84,243],"(TTA).":[86],"Without":[87],"TTA,":[88],"DEIMv2-S":[89],"achieved":[90],"79.9%":[91],"82.3%":[93],"mAP@0.5":[94,117,133],"Test_1":[96,141],"Test_2,":[98,143],"respectively,":[99],"mAP@[.5:.95]":[101,107],"37.7%":[103],"38.2%.":[105],"Its":[106],"was":[108,118,150],"comparable":[109],"to":[110],"other":[112],"query-based":[113],"detectors,":[114],"whereas":[115],"its":[116],"lower":[119],"than":[120],"that":[121],"earlier":[124],"DETR":[125],"baselines.":[126],"For":[127],"DEIMv2-S,":[128],"six-view":[129],"WBF":[130],"TTA":[131],"improved":[132],"by":[134,186],"1.4":[135],"2.1":[137],"percentage":[138],"points":[139],"respectively;":[144],"however,":[145],"same":[147],"recipe":[149],"neutral":[151],"or":[152],"detrimental":[153],"for":[154,171,230,247],"RT-DETR-R18":[155],"D-FINE-S":[157],"reduced":[159],"AR@100.":[160],"Thus,":[161],"benefit":[163],"is":[164,202],"detector-specific":[165],"should":[167],"not":[168,196],"be":[169,218],"assumed":[170],"recall-critical":[172],"applications.":[173],"further":[175],"find":[176],"12\u201316-point":[178],"gap":[179],"between":[180,208],"validation":[181],"test":[183,212],"performance,":[184],"accompanied":[185],"shifts":[187],"in":[188],"class":[189],"object-size":[191],"distributions;":[192],"histogram":[193],"matching":[194],"did":[195],"remove":[197],"this":[198],"gap;":[199],"evidence":[201],"consistent":[203],"substantial":[205],"shift":[207],"training/validation":[210],"partitions,":[213],"whose":[214],"specific":[215],"causes":[216],"cannot":[217],"identified":[219],"from":[220],"available":[222],"metadata.":[223],"The":[224],"provides":[226],"reference":[229],"current":[231],"detectors":[233],"MFLS":[235],"imagery":[236],"identifies":[238],"domain":[239],"adaptation":[240],"detector-aware":[242],"as":[245],"priorities":[246],"future":[248],"work.":[249]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-21T00:00:00"}