{"id":"https://openalex.org/W7117485420","doi":"https://doi.org/10.1109/dicta68720.2025.11302479","title":"Filling the Gaps: A Multitask Hybrid Multiscale Generative Framework for Missing Modality in Remote Sensing Semantic Segmentation","display_name":"Filling the Gaps: A Multitask Hybrid Multiscale Generative Framework for Missing Modality in Remote Sensing Semantic Segmentation","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7117485420","doi":"https://doi.org/10.1109/dicta68720.2025.11302479"},"language":null,"primary_location":{"id":"doi:10.1109/dicta68720.2025.11302479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta68720.2025.11302479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","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/A5121499869","display_name":"Nhi Kieu","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Nhi Kieu","raw_affiliation_strings":["School of Electrical Engineering and Robotics, Queensland University of Technology,Brisbane,QLD,Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Robotics, Queensland University of Technology,Brisbane,QLD,Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021261421","display_name":"Kien T. Nguyen","orcid":"https://orcid.org/0000-0003-2685-3928"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kien Nguyen","raw_affiliation_strings":["School of Electrical Engineering and Robotics, Queensland University of Technology,Brisbane,QLD,Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Robotics, Queensland University of Technology,Brisbane,QLD,Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121454378","display_name":"Arnold Wiliem","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Arnold Wiliem","raw_affiliation_strings":["School of Electrical Engineering and Robotics, Queensland University of Technology,Brisbane,QLD,Australia","Shield AI"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Robotics, Queensland University of Technology,Brisbane,QLD,Australia","institution_ids":["https://openalex.org/I160993911"]},{"raw_affiliation_string":"Shield AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034095159","display_name":"Clinton Fookes","orcid":"https://orcid.org/0000-0002-8515-6324"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Clinton Fookes","raw_affiliation_strings":["School of Electrical Engineering and Robotics, Queensland University of Technology,Brisbane,QLD,Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Robotics, Queensland University of Technology,Brisbane,QLD,Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121448206","display_name":"Sridha Sridharan","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sridha Sridharan","raw_affiliation_strings":["School of Electrical Engineering and Robotics, Queensland University of Technology,Brisbane,QLD,Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Robotics, Queensland University of Technology,Brisbane,QLD,Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121454378","display_name":"Arnold Wiliem","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Arnold Wiliem","raw_affiliation_strings":["School of Electrical Engineering and Robotics, Queensland University of Technology,Brisbane,QLD,Australia","Shield AI"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Robotics, Queensland University of Technology,Brisbane,QLD,Australia","institution_ids":["https://openalex.org/I160993911"]},{"raw_affiliation_string":"Shield AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5121499869"],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69383032,"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":0.7750999927520752,"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":0.7750999927520752,"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":0.04320000112056732,"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/T13282","display_name":"Automated Road and Building Extraction","score":0.03750000149011612,"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/generative-grammar","display_name":"Generative grammar","score":0.5950999855995178},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5303999781608582},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4643000066280365},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.46380001306533813},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4634999930858612},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4602999985218048},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4530999958515167},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.44510000944137573},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.42419999837875366},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4106000065803528}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.779699981212616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6071000099182129},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5950999855995178},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5303999781608582},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.46380001306533813},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4634999930858612},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4602999985218048},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41440001130104065},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4106000065803528},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.3917999863624573},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.334199994802475},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dicta68720.2025.11302479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta68720.2025.11302479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2800744393","https://openalex.org/W2885826602","https://openalex.org/W2963073614","https://openalex.org/W2995709945","https://openalex.org/W2997534433","https://openalex.org/W3007486523","https://openalex.org/W3048631361","https://openalex.org/W3091791645","https://openalex.org/W3092711945","https://openalex.org/W3127739228","https://openalex.org/W3173890719","https://openalex.org/W3176404283","https://openalex.org/W3184679245","https://openalex.org/W4200005911","https://openalex.org/W4205365435","https://openalex.org/W4226252548","https://openalex.org/W4285190744","https://openalex.org/W4288391270","https://openalex.org/W4295938041","https://openalex.org/W4313164293","https://openalex.org/W4313340471","https://openalex.org/W4361856922","https://openalex.org/W4364321555","https://openalex.org/W4385245566","https://openalex.org/W4386071994","https://openalex.org/W4386076642","https://openalex.org/W4394730853","https://openalex.org/W4399258843","https://openalex.org/W4402703093","https://openalex.org/W4404689784"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"learning":[1,145],"has":[2],"shown":[3],"significant":[4],"performance":[5],"boost":[6],"compared":[7],"to":[8,23,58,118,157,169,182],"ordinary":[9],"unimodal":[10],"models":[11,41,115],"across":[12,174,190],"various":[13],"domains.":[14],"However,":[15],"in":[16,68,87,101],"real-world":[17],"scenarios,":[18],"multimodal":[19,92],"signals":[20],"are":[21,54,116],"susceptible":[22,117],"missing":[24,60,132],"because":[25],"of":[26,83,91],"sensor":[27],"failures":[28],"and":[29,38,49,107,176,192,205,211,223],"adverse":[30],"weather":[31],"conditions,":[32],"which":[33],"drastically":[34],"deteriorates":[35],"models'":[36],"operation":[37],"performance.":[39],"Generative":[40,50],"such":[42],"as":[43],"AutoEncoder":[44],"(<tex":[45],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[46,231,233],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$A":[47],"E$</tex>)":[48],"Adversarial":[51],"Network":[52,146],"(GAN)":[53],"intuitive":[55],"solutions":[56],"aiming":[57],"reconstruct":[59],"modality":[61,133],"from":[62],"available":[63,229],"ones.":[64],"Yet,":[65],"their":[66],"efficacy":[67],"remote":[69,93,219],"sensing":[70,94,220],"semantic":[71,99,172,217],"segmentation":[72,218],"remains":[73],"underexplored.":[74],"In":[75,111],"this":[76],"paper,":[77],"we":[78,139],"first":[79],"examine":[80],"the":[81,89,122,184],"limitations":[82],"existing":[84],"generative":[85,114,199],"approaches":[86,208],"handling":[88],"heterogeneity":[90],"data.":[95],"They":[96],"inadequately":[97],"capture":[98,170],"context":[100,173],"complex":[102],"scenes":[103],"with":[104,148,165],"large":[105],"intra-class":[106],"small":[108],"inter-class":[109],"variation.":[110],"addition,":[112],"traditional":[113],"heavy":[119],"dependence":[120],"on":[121,214],"dominant":[123],"modality,":[124],"introducing":[125],"bias":[126,186],"that":[127],"affects":[128],"model":[129],"robustness":[130],"under":[131],"conditions.":[134],"To":[135],"tackle":[136],"these":[137],"limitations,":[138],"propose":[140],"a":[141],"novel":[142],"Generative-Enhanced":[143],"MultiModal":[144],"(GEMMNet)":[147],"three":[149],"key":[150],"components:":[151],"(1)":[152],"Hybrid":[153,163],"Feature":[154],"Extractor":[155],"(HyFEx)":[156],"effectively":[158],"learn":[159],"modality-specific":[160],"representations,":[161],"(2)":[162],"Fusion":[164],"Multiscale":[166],"Awareness":[167],"(HyFMA)":[168],"modality-synergistic":[171],"scales":[175],"(3)":[177],"Complementary":[178],"Loss":[179],"(CoLoss)":[180],"scheme":[181],"alleviate":[183],"inherent":[185],"by":[187],"encouraging":[188],"consistency":[189],"modalities":[191],"tasks.":[193],"Our":[194],"method,":[195],"GEMMNet,":[196],"outperforms":[197],"both":[198],"baselines":[200],"AE,":[201],"cGAN":[202],"(conditional":[203],"GAN),":[204],"state-of-the-art":[206],"non-generative":[207],"-":[209,213],"mmformer":[210],"shaspec":[212],"two":[215],"challenging":[216],"datasets":[221],"(Vaihingen":[222],"Potsdam).":[224],"Source":[225],"code":[226],"is":[227],"made":[228],"here<sup":[230],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[232],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>https://github.com/nhikieu/GEMMNet.":[234]},"counts_by_year":[],"updated_date":"2025-12-30T23:08:21.542490","created_date":"2025-12-29T00:00:00"}