{"id":"https://openalex.org/W7147387884","doi":"https://doi.org/10.48550/arxiv.2603.28182","title":"A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helps","display_name":"A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helps","publication_year":2026,"publication_date":"2026-03-30","ids":{"openalex":"https://openalex.org/W7147387884","doi":"https://doi.org/10.48550/arxiv.2603.28182"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.28182","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28182","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.28182","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054286686","display_name":"Xuanlong Yu","orcid":"https://orcid.org/0000-0001-8438-5187"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Xuanlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025080531","display_name":"Youyang Sha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sha, Youyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132580145","display_name":"Longfei Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Longfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132604824","display_name":"Xi Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Xi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132676077","display_name":"Di Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Di","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.4853000044822693,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.4853000044822693,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.44429999589920044,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.011900000274181366,"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/robustness","display_name":"Robustness (evolution)","score":0.619700014591217},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5885000228881836},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.5680999755859375},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5163000226020813},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.39969998598098755},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.3578000068664551},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3409000039100647},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.3264999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.824400007724762},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.619700014591217},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5885000228881836},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5680999755859375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5209000110626221},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5163000226020813},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49880000948905945},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2976999878883362},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2847999930381775},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.2508000135421753},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.28182","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28182","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.28182","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28182","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":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Few-shot":[0],"object":[1],"detection":[2],"(FSOD)":[3],"is":[4,206],"challenging":[5],"due":[6],"to":[7,67,90,176,179,189],"unstable":[8],"optimization":[9,109],"and":[10,81,110,128,199],"limited":[11],"generalization":[12,32],"arising":[13],"from":[14,60,174],"the":[15,39,61,82,131,155,160,196,202],"scarcity":[16],"of":[17,133,152,201],"training":[18],"samples.":[19],"To":[20],"address":[21],"these":[22],"issues,":[23],"we":[24],"propose":[25],"a":[26,42,96,102,170],"hybrid":[27],"ensemble":[28,37],"decoder":[29,40,50],"that":[30,184],"enhances":[31],"during":[33],"fine-tuning.":[34],"Inspired":[35],"by":[36,47],"learning,":[38],"comprises":[41],"shared":[43,62],"hierarchical":[44],"layer":[45,63],"followed":[46],"multiple":[48],"parallel":[49],"branches,":[51],"where":[52],"each":[53],"branch":[54],"employs":[55],"denoising":[56],"queries":[57],"either":[58],"inherited":[59],"or":[64,119],"newly":[65],"initialized":[66],"encourage":[68],"prediction":[69],"diversity.":[70],"This":[71],"design":[72],"fully":[73],"exploits":[74],"pretrained":[75],"weights":[76],"without":[77,115],"introducing":[78],"additional":[79],"parameters,":[80],"resulting":[83],"diverse":[84,144],"predictions":[85],"can":[86],"be":[87],"effectively":[88],"ensembled":[89],"improve":[91],"generalization.":[92],"We":[93,167],"further":[94,168],"leverage":[95],"unified":[97],"progressive":[98],"fine-tuning":[99],"framework":[100],"with":[101],"plateau-aware":[103],"learning":[104],"rate":[105],"schedule,":[106],"which":[107,139,164],"stabilizes":[108],"achieves":[111,148],"strong":[112],"few-shot":[113],"adaptation":[114],"complex":[116],"data":[117],"augmentations":[118],"extensive":[120],"hyperparameter":[121],"tuning.":[122],"Extensive":[123],"experiments":[124],"on":[125,137],"CD-FSOD,":[126],"ODinW-13,":[127],"RF100-VL":[129],"validate":[130],"effectiveness":[132],"our":[134,146,185],"approach.":[135],"Notably,":[136],"RF100-VL,":[138],"includes":[140],"100":[141],"datasets":[142],"across":[143],"domains,":[145],"method":[147],"an":[149],"average":[150],"performance":[151],"41.9":[153],"in":[154],"10-shot":[156],"setting,":[157],"significantly":[158],"outperforming":[159],"recent":[161],"approach":[162],"SAM3,":[163],"obtains":[165],"35.7.":[166],"construct":[169],"mixed-domain":[171],"test":[172],"set":[173],"CD-FSOD":[175],"evaluate":[177],"robustness":[178,200],"out-of-distribution":[180],"(OOD)":[181],"samples,":[182],"showing":[183],"proposed":[186,203],"modules":[187],"lead":[188],"clear":[190],"improvement":[191],"gains.":[192],"These":[193],"results":[194],"highlight":[195],"effectiveness,":[197],"generalization,":[198],"method.":[204],"Code":[205],"available":[207],"at:":[208],"https://github.com/Intellindust-AI-Lab/FT-FSOD.":[209]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-02T00:00:00"}