{"id":"https://openalex.org/W4319300007","doi":"https://doi.org/10.1109/wacv56688.2023.00377","title":"Transformers For Recognition In Overhead Imagery: A Reality Check","display_name":"Transformers For Recognition In Overhead Imagery: A Reality Check","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4319300007","doi":"https://doi.org/10.1109/wacv56688.2023.00377"},"language":"en","primary_location":{"id":"doi:10.1109/wacv56688.2023.00377","doi":"https://doi.org/10.1109/wacv56688.2023.00377","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/wacv56688.2023.00377","pdf_url":null,"source":{"id":"https://openalex.org/S4393918690","display_name":"IEEE Winter Conference on Applications of Computer Vision","issn_l":"2472-6737","issn":["2472-6737"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.12599","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081327514","display_name":"Francesco Luzi","orcid":"https://orcid.org/0000-0001-7784-2220","observed_orcids":["https://orcid.org/0000-0001-7784-2220"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Francesco Luzi","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101194545","display_name":"Aneesh Gupta","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aneesh Gupta","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004578492","display_name":"Leslie M. Collins","orcid":"https://orcid.org/0000-0002-9043-6531","observed_orcids":["https://orcid.org/0000-0002-9043-6531"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leslie Collins","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054438743","display_name":"Kyle Bradbury","orcid":"https://orcid.org/0000-0001-9847-0243","observed_orcids":["https://orcid.org/0000-0001-9847-0243"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Bradbury","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007239332","display_name":"Jordan M. Malof","orcid":"https://orcid.org/0000-0002-7851-4920","observed_orcids":["https://orcid.org/0000-0002-7851-4920"]},"institutions":[{"id":"https://openalex.org/I6750721","display_name":"University of Montana","ror":"https://ror.org/0078xmk34","country_code":"US","type":"education","lineage":["https://openalex.org/I6750721"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jordan Malof","raw_affiliation_strings":["University of Montana"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Montana","institution_ids":["https://openalex.org/I6750721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4281,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68559286,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3767","last_page":"3776"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8798999786376953,"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":0.8798999786376953,"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":0.11100000143051147,"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/T13282","display_name":"Automated Road and Building Extraction","score":0.00279999990016222,"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/transformer","display_name":"transformer models","score":0.7419999837875366},{"id":"https://openalex.org/keywords/overhead-imagery","display_name":"overhead imagery","score":0.8489999771118164},{"id":"https://openalex.org/keywords/satellite-imagery","display_name":"satellite imagery","score":0.753000020980835},{"id":"https://openalex.org/keywords/semantic-segmentation","display_name":"semantic segmentation","score":0.8140000104904175},{"id":"https://openalex.org/keywords/model-comparison","display_name":"model comparison","score":0.671999990940094},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.5569999814033508},{"id":"https://openalex.org/keywords/inria","display_name":"INRIA","score":0.5009999871253967},{"id":"https://openalex.org/keywords/deepglobe","display_name":"DeepGlobe","score":1.0}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7228091359138489},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6939365863800049},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6855530142784119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5037228465080261},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4908626675605774},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4899856150150299},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4762442409992218},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.41937392950057983},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15683090686798096},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08431792259216309},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv56688.2023.00377","doi":"https://doi.org/10.1109/wacv56688.2023.00377","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/wacv56688.2023.00377","pdf_url":null,"source":{"id":"https://openalex.org/S4393918690","display_name":"IEEE Winter Conference on Applications of Computer Vision","issn_l":"2472-6737","issn":["2472-6737"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2210.12599","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.12599","pdf_url":"https://arxiv.org/pdf/2210.12599","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2210.12599","doi":"https://doi.org/10.48550/arxiv.2210.12599","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.12599","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.12599","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.12599","pdf_url":"https://arxiv.org/pdf/2210.12599","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4943999946117401,"id":"https://metadata.un.org/sdg/9"}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306151","display_name":"Alfred P. Sloan Foundation","ror":"https://ror.org/052csg198"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319300007.pdf","grobid_xml":"https://content.openalex.org/works/W4319300007.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1510052597","https://openalex.org/W1665214252","https://openalex.org/W1836465849","https://openalex.org/W1901129140","https://openalex.org/W2131241448","https://openalex.org/W2194775991","https://openalex.org/W2432481613","https://openalex.org/W2609402060","https://openalex.org/W2747402019","https://openalex.org/W2782757030","https://openalex.org/W2787225861","https://openalex.org/W2804199516","https://openalex.org/W2804962028","https://openalex.org/W2806581075","https://openalex.org/W2884436604","https://openalex.org/W2907750714","https://openalex.org/W2922544158","https://openalex.org/W2950628590","https://openalex.org/W2963150697","https://openalex.org/W2964227007","https://openalex.org/W2964309882","https://openalex.org/W3009522002","https://openalex.org/W3011515952","https://openalex.org/W3011927872","https://openalex.org/W3015788359","https://openalex.org/W3037932933","https://openalex.org/W3044947951","https://openalex.org/W3048802707","https://openalex.org/W3094502228","https://openalex.org/W3115190122","https://openalex.org/W3127751679","https://openalex.org/W3138516171","https://openalex.org/W3156621598","https://openalex.org/W3161120562","https://openalex.org/W3161790566","https://openalex.org/W3171660447","https://openalex.org/W3178812510","https://openalex.org/W3204255739","https://openalex.org/W3204614423","https://openalex.org/W3205020875","https://openalex.org/W3209987414","https://openalex.org/W3211329537","https://openalex.org/W3212076252","https://openalex.org/W4205138939","https://openalex.org/W4214760051","https://openalex.org/W4221146106","https://openalex.org/W4283450732","https://openalex.org/W4312919733","https://openalex.org/W4321232185","https://openalex.org/W4323274164","https://openalex.org/W6747680804","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W6948233274","https://openalex.org/W4220693311","https://openalex.org/W3119997354","https://openalex.org/W4405440899","https://openalex.org/W4376983087","https://openalex.org/W3119786062","https://openalex.org/W4319985630","https://openalex.org/W4412586020","https://openalex.org/W4313140053","https://openalex.org/W3204538018"],"abstract_inverted_index":{"There":[0],"is":[1,19,64],"evidence":[2],"that":[3,124,141],"transformers":[4,125],"offer":[5],"state-of-the-art":[6,56],"recognition":[7],"performance":[8,130],"on":[9],"tasks":[10],"involving":[11],"overhead":[12,60],"imagery":[13],"(e.g.,":[14],"satellite":[15],"imagery).":[16],"However,":[17],"it":[18,32],"difficult":[20],"to":[21,36,112],"make":[22],"unbiased":[23],"empirical":[24],"comparisons":[25],"between":[26],"competing":[27],"deep":[28],"learning":[29],"models,":[30],"making":[31],"unclear":[33],"whether,":[34],"and":[35,72,86,96,105,144],"what":[37],"extent,":[38],"transformer-based":[39,118,145,149],"models":[40,58,140,150],"are":[41,75],"beneficial.":[42],"In":[43],"this":[44,135],"paper":[45],"we":[46],"systematically":[47],"compare":[48],"the":[49,114],"impact":[50,115],"of":[51,69,84,116],"adding":[52],"transformer":[53],"structures":[54],"into":[55],"segmentation":[57],"for":[59],"imagery.":[61],"Each":[62],"model":[63],"given":[65],"a":[66,81,94],"similar":[67],"budget":[68],"free":[70],"parameters,":[71],"their":[73],"hyperparameters":[74],"optimized":[76],"using":[77],"Bayesian":[78],"Optimization":[79],"with":[80,93],"fixed":[82],"quantity":[83],"data":[85],"computation":[87],"time.":[88],"We":[89,107,132],"conduct":[90],"our":[91],"experiments":[92],"large":[95,101],"diverse":[97],"dataset":[98],"comprising":[99],"two":[100],"public":[102],"benchmarks:":[103],"Inria":[104],"DeepGlobe.":[106],"perform":[108],"additional":[109],"ablation":[110],"studies":[111],"explore":[113],"specific":[117],"modeling":[119],"choices.":[120],"Our":[121],"results":[122],"suggest":[123],"provide":[126],"consistent,":[127],"but":[128],"modest,":[129],"improvements.":[131],"only":[133],"observe":[134],"advantage":[136],"however":[137],"in":[138],"hybrid":[139],"combine":[142],"convolutional":[143],"structures,":[146],"while":[147],"fully":[148],"achieve":[151],"relatively":[152],"poor":[153],"performance.":[154]},"counts_by_year":[{"year":2024,"cited_by_count":4}],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2023-02-07T00:00:00"}