{"id":"https://openalex.org/W4386875228","doi":"https://doi.org/10.48550/arxiv.2309.09003","title":"RingMo-lite: A Remote Sensing Multi-task Lightweight Network with CNN-Transformer Hybrid Framework","display_name":"RingMo-lite: A Remote Sensing Multi-task Lightweight Network with CNN-Transformer Hybrid Framework","publication_year":2023,"publication_date":"2023-09-16","ids":{"openalex":"https://openalex.org/W4386875228","doi":"https://doi.org/10.48550/arxiv.2309.09003"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2309.09003","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.09003","pdf_url":"https://arxiv.org/pdf/2309.09003","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.09003","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073939784","display_name":"Yuelei Wang","orcid":"https://orcid.org/0000-0002-3897-7672","observed_orcids":["https://orcid.org/0000-0002-3897-7672"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yuelei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100738839","display_name":"Ting Zhang","orcid":"https://orcid.org/0000-0002-1899-1784","observed_orcids":["https://orcid.org/0000-0002-1899-1784","https://orcid.org/0009-0001-1967-713X","https://orcid.org/0000-0002-5748-9754","https://orcid.org/0009-0009-0822-1469"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089561905","display_name":"Liangjin Zhao","orcid":"https://orcid.org/0000-0002-2590-591X","observed_orcids":["https://orcid.org/0000-0002-2590-591X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Liangjin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103290979","display_name":"Lin Hu","orcid":"https://orcid.org/0009-0009-0647-8391","observed_orcids":["https://orcid.org/0009-0009-0647-8391","https://orcid.org/0000-0001-7932-235X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062002874","display_name":"Zhechao Wang","orcid":"https://orcid.org/0000-0002-4082-0199","observed_orcids":["https://orcid.org/0000-0002-4082-0199"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhechao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102557726","display_name":"Ziqing Niu","orcid":"https://orcid.org/0009-0003-4539-5923","observed_orcids":["https://orcid.org/0009-0003-4539-5923"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niu, Ziqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007124311","display_name":"Peirui Cheng","orcid":"https://orcid.org/0000-0002-4993-6753","observed_orcids":["https://orcid.org/0000-0002-4993-6753"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Peirui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053611461","display_name":"Kaiqiang Chen","orcid":"https://orcid.org/0000-0002-8314-2375","observed_orcids":["https://orcid.org/0000-0002-8314-2375","https://orcid.org/0000-0002-0269-3651"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Kaiqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112124444","display_name":"Xuan Zeng","orcid":"https://orcid.org/0009-0002-3063-5800","observed_orcids":["https://orcid.org/0009-0002-3063-5800"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Xuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023538862","display_name":"Zhirui Wang","orcid":"https://orcid.org/0000-0003-2877-0384","observed_orcids":["https://orcid.org/0000-0003-2877-0384","https://orcid.org/0009-0001-8113-2632","https://orcid.org/0009-0007-7814-0811","https://orcid.org/0009-0008-2338-0049"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhirui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001093841","display_name":"Hongqi Wang","orcid":"https://orcid.org/0000-0002-5172-571X","observed_orcids":["https://orcid.org/0000-0002-5172-571X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Hongqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005905514","display_name":"Xian Sun","orcid":"https://orcid.org/0000-0002-0038-9816","observed_orcids":["https://orcid.org/0000-0002-0038-9816","https://orcid.org/0009-0009-0598-6941"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Xian","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":5,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.6977999806404114,"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":0.6977999806404114,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.2912999987602234,"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/T13890","display_name":"Remote Sensing and Land Use","score":0.002099999925121665,"subfield":{"id":"https://openalex.org/subfields/1902","display_name":"Atmospheric Science"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/remote-sensing-image-interpretation","display_name":"remote sensing interpretation","score":0.9570000171661377},{"id":"https://openalex.org/keywords/hybrid-cnn-transformer-model","display_name":"CNN-Transformer hybrid","score":0.8700000047683716},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.6629999876022339},{"id":"https://openalex.org/keywords/edge-devices","display_name":"edge devices","score":0.6790000200271606},{"id":"https://openalex.org/keywords/parameter-reduction","display_name":"parameter reduction","score":0.4519999921321869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7836593389511108},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7030035853385925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5045768022537231},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.42666029930114746},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35365837812423706},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.15878665447235107},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09807440638542175},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2309.09003","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.09003","pdf_url":"https://arxiv.org/pdf/2309.09003","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2309.09003","doi":"https://doi.org/10.48550/arxiv.2309.09003","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2309.09003","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.09003","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.09003","pdf_url":"https://arxiv.org/pdf/2309.09003","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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/W4391594089","https://openalex.org/W4417305260","https://openalex.org/W7125201331","https://openalex.org/W4288391486","https://openalex.org/W4405023205","https://openalex.org/W4417271143","https://openalex.org/W4403279492","https://openalex.org/W4412171137","https://openalex.org/W4410028595","https://openalex.org/W7127367550"],"abstract_inverted_index":{"In":[0,235],"recent":[1],"years,":[2],"remote":[3],"sensing":[4],"(RS)":[5],"vision":[6],"foundation":[7,46],"models":[8,34,230],"such":[9],"as":[10,131,150],"RingMo":[11],"have":[12],"emerged":[13],"and":[14,76,146,177,224],"achieved":[15],"excellent":[16],"performance":[17,227],"in":[18,58,65,80,161,186,191,205,219,247],"various":[19,206],"downstream":[20],"tasks.":[21],"However,":[22],"the":[23,30,73,94,114,121,128,147,162,165,182,197,201,211,222,232,243,248],"high":[24,75],"demand":[25],"for":[26,93],"computing":[27,245],"resources":[28],"limits":[29],"application":[31],"of":[32,117,139,221,231],"these":[33],"on":[35],"edge":[36],"devices.":[37],"It":[38,124],"is":[39,70,125],"necessary":[40],"to":[41,48,72,119,135,155,229],"design":[42],"a":[43,107,132,143,151],"more":[44],"lightweight":[45,60,104],"model":[47],"support":[49],"on-orbit":[50],"RS":[51,66,81,102,118,140,187,207],"image":[52,67,169,174,208],"interpretation.":[53,68],"Existing":[54],"methods":[55,91],"face":[56],"challenges":[57],"achieving":[59],"solutions":[61],"while":[62],"retaining":[63],"generalization":[64],"This":[69],"due":[71],"complex":[74],"low-frequency":[77,178],"spectral":[78],"components":[79],"images,":[82],"which":[83,111],"make":[84],"traditional":[85],"single":[86],"CNN":[87,148],"or":[88],"Vision":[89],"Transformer":[90,129],"unsuitable":[92],"task.":[95],"Therefore,":[96],"this":[97],"paper":[98],"proposes":[99],"RingMo-lite,":[100],"an":[101],"multi-task":[103],"network":[105],"with":[106,195],"CNN-Transformer":[108],"hybrid":[109],"framework,":[110],"effectively":[112,180],"exploits":[113],"frequency-domain":[115,167],"properties":[116],"optimize":[120],"interpretation":[122,209],"process.":[123],"combined":[126],"by":[127,215],"module":[130,149],"low-pass":[133],"filter":[134,154],"extract":[136,156],"global":[137],"features":[138],"images":[141],"through":[142],"dual-branch":[144],"structure,":[145],"stacked":[152],"high-pass":[153],"fine-grained":[157],"details":[158],"effectively.":[159],"Furthermore,":[160],"pretraining":[163],"stage,":[164],"designed":[166],"masked":[168],"modeling":[170],"(FD-MIM)":[171],"combines":[172],"each":[173],"patch's":[175],"high-frequency":[176],"characteristics,":[179],"capturing":[181],"latent":[183],"feature":[184],"representation":[185],"data.":[188],"As":[189],"shown":[190],"Fig.":[192],"1,":[193],"compared":[194,228],"RingMo,":[196],"proposed":[198],"RingMo-lite":[199],"reduces":[200],"parameters":[202],"over":[203],"60%":[204],"tasks,":[210],"average":[212],"accuracy":[213],"drops":[214],"less":[216],"than":[217],"2%":[218],"most":[220],"scenes":[223],"achieves":[225],"SOTA":[226],"similar":[233],"size.":[234],"addition,":[236],"our":[237],"work":[238],"will":[239],"be":[240],"integrated":[241],"into":[242],"MindSpore":[244],"platform":[246],"near":[249],"future.":[250]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4}],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2023-09-20T00:00:00"}