{"id":"https://openalex.org/W4416213812","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227996","title":"From Echo Distillation to Chat-Driven: A Multi-Task VLM is OK for Object Detection and Fine-Grained Classification in Remote Sensing Images","display_name":"From Echo Distillation to Chat-Driven: A Multi-Task VLM is OK for Object Detection and Fine-Grained Classification in Remote Sensing Images","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416213812","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227996"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227996","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5040060555","display_name":"Liuqian Wang","orcid":"https://orcid.org/0000-0002-4127-1283"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liuqian Wang","raw_affiliation_strings":["Beijing University of Technology,School of Information Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,School of Information Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014482509","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0003-2541-4923"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Beijing University of Technology,School of Information Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,School of Information Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112317474","display_name":"Guangyong Mi","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Mi","raw_affiliation_strings":["Beijing University of Technology,School of Information Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,School of Information Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100448036","display_name":"Zhuo Li","orcid":"https://orcid.org/0000-0002-9937-2669"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhuo","raw_affiliation_strings":["Beijing University of Technology,School of Information Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,School of Information Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040060555"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48647594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.3416999876499176,"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":0.3416999876499176,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.2599000036716461,"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":0.15029999613761902,"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/object-detection","display_name":"Object detection","score":0.7106000185012817},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6082000136375427},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5543000102043152},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5299999713897705},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4952999949455261},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45190000534057617},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38280001282691956},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.376800000667572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.777999997138977},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7106000185012817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6553000211715698},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6082000136375427},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5543000102043152},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5299999713897705},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4952999949455261},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.48590001463890076},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4575999975204468},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C183365957","wikidata":"https://www.wikidata.org/wiki/Q17140402","display_name":"Remote sensing application","level":3,"score":0.3203999996185303},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.30059999227523804},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29649999737739563},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2854999899864197},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227996","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2176924101","https://openalex.org/W2194775991","https://openalex.org/W2964979676","https://openalex.org/W3016719260","https://openalex.org/W3136761610","https://openalex.org/W3138516171","https://openalex.org/W3174873843","https://openalex.org/W3201797941","https://openalex.org/W4214648418","https://openalex.org/W4312804579","https://openalex.org/W4360770920","https://openalex.org/W4386072246","https://openalex.org/W4386076493","https://openalex.org/W4389880076","https://openalex.org/W4390873076","https://openalex.org/W4391559729","https://openalex.org/W4400366382","https://openalex.org/W4401634048","https://openalex.org/W4402352155","https://openalex.org/W4402776460","https://openalex.org/W4403193080","https://openalex.org/W4404914450","https://openalex.org/W4405895891"],"related_works":[],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"(VLMs)":[2],"have":[3],"demonstrated":[4],"attracting":[5],"performance":[6,106],"in":[7,28,39,46,79,149],"natural":[8],"image":[9],"domains,":[10],"and":[11,19,48,76,94,127,151,162,172,184,192],"their":[12],"application":[13],"to":[14,64,97,123,157],"multitask":[15],"remote":[16,29],"sensing":[17,30],"analysis":[18],"interpretation":[20],"holds":[21],"great":[22],"potential.":[23],"However,":[24],"realizing":[25],"this":[26],"potential":[27],"images":[31],"(RSIs)":[32],"is":[33],"hindered":[34],"by":[35],"limited":[36],"feature":[37,100],"extraction":[38],"lightweight":[40,109],"detectors,":[41],"loss":[42],"of":[43,51,107,179],"fine-grained":[44,77,125,147,198],"details":[45,126],"classification,":[47],"the":[49,104,108,121,177,188,197],"lack":[50],"unified":[52],"multi-task":[53,60,155,164],"frameworks.":[54],"In":[55],"response,":[56],"we":[57,82,112,138],"propose":[58],"a":[59,114,141,153],"vision-language":[61],"model":[62,122],"(MT-VLM)":[63],"address":[65],"these":[66],"limitations,":[67],"offering":[68],"an":[69,85],"effective":[70],"solution":[71],"for":[72,146],"both":[73,159],"object":[74,189],"detection":[75,105,190],"classification":[78,129,148,199],"RSIs.":[80],"Specifically,":[81],"introduce":[83],"EchoDistill,":[84],"echo":[86],"distillation":[87],"framework":[88],"that":[89],"combines":[90],"teacher":[91],"knowledge":[92],"transfer":[93],"self-knowledge":[95],"reinforcement":[96],"iteratively":[98],"enhance":[99],"learning,":[101],"significantly":[102],"boosting":[103],"models.":[110],"Additionally,":[111],"develop":[113],"chat-driven":[115],"VLM":[116],"with":[117],"LoRA":[118],"fine-tuning,":[119],"enabling":[120],"capture":[124],"improve":[128],"accuracy":[130,195],"using":[131],"multimodal":[132],"embeddings.":[133],"To":[134],"support":[135],"our":[136,180],"framework,":[137],"collected":[139],"BJUT-FGC,":[140],"comprehensive":[142],"image-text":[143],"labeled":[144],"dataset":[145],"RSIs,":[150],"built":[152],"dual-mode":[154],"benchmark":[156],"facilitate":[158],"task-specific":[160],"adaptation":[161],"integrated":[163],"refinement.":[165],"Experimental":[166],"results":[167],"on":[168,187,196],"DOTA":[169],"2.0,":[170],"VEDAI,":[171],"self-built":[173],"BJUT-FGC":[174],"datasets":[175],"demonstrate":[176],"effectiveness":[178],"approach,":[181],"achieving":[182],"58.71%":[183],"82.06%":[185],"mAP":[186],"task":[191],"88.08%":[193],"top-1":[194],"task.":[200]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}