{"id":"https://openalex.org/W4401416386","doi":"https://doi.org/10.1109/icra57147.2024.10610358","title":"Learning Multi-Scale Context Mask-RCNN Network for Slant Angled Aerial Imagery in Instance Segmentation in a Sim2Real setup","display_name":"Learning Multi-Scale Context Mask-RCNN Network for Slant Angled Aerial Imagery in Instance Segmentation in a Sim2Real setup","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416386","doi":"https://doi.org/10.1109/icra57147.2024.10610358"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5106356742","display_name":"Qiranul Saadiyean","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Qiranul Saadiyean","raw_affiliation_strings":["Indian Institute of Science,Department of Aerospace Engineering"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Department of Aerospace Engineering","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089299800","display_name":"S P Samprithi","orcid":null},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S P Samprithi","raw_affiliation_strings":["PES University,Department of Electronics and Communication Engineering"],"affiliations":[{"raw_affiliation_string":"PES University,Department of Electronics and Communication Engineering","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100765440","display_name":"Suresh Sundaram","orcid":"https://orcid.org/0000-0001-6275-0921"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Suresh Sundaram","raw_affiliation_strings":["Indian Institute of Science,Department of Aerospace Engineering"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Department of Aerospace Engineering","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5106356742"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":1.2504,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80647055,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"13573","last_page":"13580"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991000294685364,"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/aerial-imagery","display_name":"Aerial imagery","score":0.7512085437774658},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6742808818817139},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.6634954214096069},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6619173288345337},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6581001877784729},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.624401330947876},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5985525846481323},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5340641140937805},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.44449812173843384},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19168898463249207},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.18807876110076904},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.14013147354125977},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.13848519325256348}],"concepts":[{"id":"https://openalex.org/C2987819851","wikidata":"https://www.wikidata.org/wiki/Q191839","display_name":"Aerial imagery","level":2,"score":0.7512085437774658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6742808818817139},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.6634954214096069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6619173288345337},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6581001877784729},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.624401330947876},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5985525846481323},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5340641140937805},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.44449812173843384},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19168898463249207},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.18807876110076904},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.14013147354125977},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.13848519325256348},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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":48,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1550219794","https://openalex.org/W1861492603","https://openalex.org/W2038642313","https://openalex.org/W2152272347","https://openalex.org/W2153942085","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2308318555","https://openalex.org/W2412782625","https://openalex.org/W2487365028","https://openalex.org/W2515866431","https://openalex.org/W2565639579","https://openalex.org/W2594177559","https://openalex.org/W2884367402","https://openalex.org/W2920326761","https://openalex.org/W2962749812","https://openalex.org/W2962777203","https://openalex.org/W2962921175","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963840672","https://openalex.org/W2989676862","https://openalex.org/W3035358681","https://openalex.org/W3039368862","https://openalex.org/W3105054740","https://openalex.org/W3105577662","https://openalex.org/W3106250896","https://openalex.org/W3118843071","https://openalex.org/W3135922489","https://openalex.org/W3176270344","https://openalex.org/W3205363943","https://openalex.org/W3210997132","https://openalex.org/W4205231989","https://openalex.org/W4226283626","https://openalex.org/W4250482878","https://openalex.org/W4307411952","https://openalex.org/W4311367439","https://openalex.org/W4319336200","https://openalex.org/W4391341364","https://openalex.org/W4402716431","https://openalex.org/W6618372016","https://openalex.org/W6620707391","https://openalex.org/W6696085341","https://openalex.org/W6763251565","https://openalex.org/W6858912597"],"related_works":["https://openalex.org/W1522196789","https://openalex.org/W4283696875","https://openalex.org/W3110585990","https://openalex.org/W4385767632","https://openalex.org/W2898690910","https://openalex.org/W2784132289","https://openalex.org/W4286697184","https://openalex.org/W2889700547","https://openalex.org/W2889866244","https://openalex.org/W3034139063"],"abstract_inverted_index":{"While":[0],"instance":[1,189],"segmentation":[2,190],"models":[3],"excel":[4],"at":[5],"object":[6],"detection":[7],"in":[8,188,197],"satellite":[9],"imagery,":[10],"their":[11],"performance":[12,186],"drops":[13],"when":[14],"applied":[15],"to":[16,21,66,118,133,167],"slant-angled":[17,58],"aerial":[18,59],"images":[19],"due":[20],"occlusion":[22],"and":[23,40,103,122,140,178],"scale":[24],"variation.":[25],"This":[26],"is":[27,64,80],"mainly":[28],"caused":[29],"by":[30],"a":[31,183,194],"lack":[32],"of":[33,72,88],"training":[34,75],"data":[35,151,157],"for":[36,57,68,93,126],"such":[37],"diverse":[38,95],"viewpoints":[39],"scales.":[41],"To":[42],"address":[43,119],"this":[44,149],"limitation,":[45],"we":[46],"propose":[47],"the":[48,69,86,90,123,168,172,179],"Sim2Real-based":[49,61],"Multi-Scale":[50],"Context":[51],"Mask-RCNN":[52],"(MSC-RCNN)":[53],"network,":[54],"specifically":[55],"designed":[56],"imagery.":[60],"transfer":[62],"learning":[63],"adapted":[65],"compensate":[67],"limited":[70],"availability":[71],"real-world":[73,91],"slant-angle":[74,96],"data.":[76],"A":[77],"synthetic":[78,150],"dataset":[79],"generated":[81],"using":[82],"Unreal":[83],"Engine,":[84],"detailing":[85],"methodology":[87],"replicating":[89],"scene,":[92],"producing":[94],"drone":[97],"datasets":[98],"with":[99,113,175,192],"various":[100,138],"weather":[101],"conditions":[102],"backgrounds.":[104],"The":[105],"model":[106,198],"leverages":[107],"two":[108],"distinct":[109],"feature":[110],"pyramid":[111],"backbones,":[112],"one":[114],"incorporating":[115,148],"dilated":[116],"convolutions":[117],"large-scale":[120],"objects":[121,136],"other":[124],"optimized":[125],"regular":[127],"convolutions.":[128],"Their":[129],"outputs":[130],"are":[131],"fused":[132],"effectively":[134],"detect":[135],"across":[137],"scales":[139],"angles.":[141],"Through":[142],"experiments,":[143],"it":[144],"was":[145],"demonstrated":[146],"that":[147],"significantly":[152],"reduces":[153],"reliance":[154],"on":[155],"real":[156],"while":[158],"maintaining":[159],"high":[160],"mean":[161],"Average":[162],"Precision":[163],"(mAP)":[164],"scores.":[165],"Compared":[166],"baseline":[169],"Mask":[170],"R-CNN,":[171],"proposed":[173],"approach":[174],"Sim2Real":[176],"adaptation":[177],"MSC-RCNN":[180],"architecture":[181],"achieves":[182],"remarkable":[184],"7.6%":[185],"improvement":[187],"accuracy":[191],"only":[193],"6%":[195],"increase":[196],"size.":[199],"Code":[200],"can":[201],"be":[202],"found":[203],"at:":[204],"https://github.com/MSC-RCNN":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}