{"id":"https://openalex.org/W7203662848","doi":"https://doi.org/10.48550/arxiv.2608.16241","title":"Convolution-Free Holistic Multivariance Decomposition Layer for Efficient Hyperspectral Image Classification Tensor Networks","display_name":"Convolution-Free Holistic Multivariance Decomposition Layer for Efficient Hyperspectral Image Classification Tensor Networks","publication_year":2026,"publication_date":"2026-08-17","ids":{"openalex":"https://openalex.org/W7203662848","doi":"https://doi.org/10.48550/arxiv.2608.16241"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.16241","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.16241","pdf_url":"https://arxiv.org/pdf/2608.16241","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/2608.16241","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011964287","display_name":"S\u00fcha Tuna","orcid":"https://orcid.org/0000-0002-9492-6896","observed_orcids":["https://orcid.org/0000-0002-9492-6896"]},"institutions":[{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Tuna, S\u00fcha","raw_affiliation_strings":["Istanbul Technical University , Informatics Institute , Maslak 34469 , \u0130stanbul , T\u00fcrkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istanbul Technical University , Informatics Institute , Maslak 34469 , \u0130stanbul , T\u00fcrkiye","institution_ids":["https://openalex.org/I48912391"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5147442040","display_name":"\u00dclker Ba\u015far","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ba\u015far, \u00dclker","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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":0.8246999979019165,"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":0.8246999979019165,"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/T12303","display_name":"Tensor decomposition and applications","score":0.16660000383853912,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.0015999999595806003,"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/hyperspectral-image-classification","display_name":"hyperspectral image classification","score":0.9950000047683716},{"id":"https://openalex.org/keywords/tensor-decomposition","display_name":"tensor decomposition","score":0.6819999814033508},{"id":"https://openalex.org/keywords/tucker-decomposition","display_name":"Tucker decomposition","score":0.8450000286102295},{"id":"https://openalex.org/keywords/canonical-polyadic-decomposition","display_name":"canonical polyadic decomposition","score":0.9309999942779541},{"id":"https://openalex.org/keywords/tensor-train-decomposition","display_name":"tensor train decomposition","score":0.871999979019165},{"id":"https://openalex.org/keywords/end-to-end-learning","display_name":"end-to-end learning","score":0.4699999988079071}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5917999744415283},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5820000171661377},{"id":"https://openalex.org/C2986737658","wikidata":"https://www.wikidata.org/wiki/Q30103009","display_name":"Tensor decomposition","level":3,"score":0.5655999779701233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5389000177383423},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5210000276565552},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5196999907493591},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.48410001397132874},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46149998903274536},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4269999861717224},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.421099990606308},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C159078339","wikidata":"https://www.wikidata.org/wiki/Q959005","display_name":"Hyperspectral imaging","level":2,"score":0.4059999883174896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3788999915122986},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.3580999970436096},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3294000029563904},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3199999928474426},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3059000074863434},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25220000743865967},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.16241","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.16241","pdf_url":"https://arxiv.org/pdf/2608.16241","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.2608.16241","doi":"https://doi.org/10.48550/arxiv.2608.16241","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.16241","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:2608.16241","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.16241","pdf_url":"https://arxiv.org/pdf/2608.16241","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203662848.pdf","grobid_xml":"https://content.openalex.org/works/W7203662848.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7171472815","https://openalex.org/W4296208460","https://openalex.org/W3172608860","https://openalex.org/W3097714985","https://openalex.org/W4296934624","https://openalex.org/W2895568661","https://openalex.org/W4312441342","https://openalex.org/W2094492907","https://openalex.org/W4391937079","https://openalex.org/W3006055389"],"abstract_inverted_index":{"Feature":[0],"extraction":[1],"for":[2,152],"hyperspectral":[3],"image":[4,158],"classification":[5,100],"is":[6],"conventionally":[7],"addressed":[8],"using":[9],"rigid":[10],"tensor":[11,106],"decompositions":[12],"that":[13,26,92,143],"fail":[14],"to":[15,103,128],"capture":[16],"complex":[17],"spatio-spectral":[18],"interdependencies,":[19],"or":[20],"heavily":[21],"parameterized":[22],"convolutional":[23],"neural":[24,48],"networks":[25],"are":[27,75],"computationally":[28],"expensive.":[29],"To":[30],"overcome":[31],"these":[32],"limitations,":[33],"this":[34],"work":[35],"introduces":[36],"the":[37,68,93,144,167],"Holistic":[38],"Multivariance":[39],"Decomposition":[40],"(HMD)":[41],"framework":[42,146],"as":[43],"a":[44,79,121,148],"novel,":[45],"end-to-end":[46],"differentiable":[47],"network":[49],"layer.":[50],"By":[51],"explicitly":[52],"separating":[53],"independent":[54],"single":[55],"mode":[56],"variations":[57],"from":[58],"cooperative":[59],"higher":[60,94],"dimensional":[61],"interactions":[62],"via":[63,82],"learnable,":[64],"matrix":[65],"valued":[66],"supports,":[67],"proposed":[69],"HMD-0,":[70],"HMD-1":[71,117],"and":[72,112,118,124,131,164],"HMD-2":[73,119],"approximants":[74],"optimized":[76],"jointly":[77],"with":[78],"downstream":[80],"classifier":[81],"backpropagation.":[83],"Comprehensive":[84],"evaluations":[85],"across":[86],"three":[87],"benchmark":[88],"HS":[89,157],"datasets":[90],"demonstrate":[91,142],"level":[95],"HMD":[96,145],"layers":[97],"achieve":[98,120],"superior":[99],"accuracy":[101],"compared":[102],"classical":[104],"learnable":[105],"baselines,":[107],"including":[108],"Tucker,":[109],"Canonical":[110],"Polyadic,":[111],"Tensor":[113],"Train":[114],"decompositions.":[115],"Furthermore,":[116],"generalization":[122],"capacity":[123],"training":[125],"stability":[126,165],"comparable":[127],"standard":[129],"2D":[130],"3D-CNNs":[132],"while":[133],"requiring":[134],"significantly":[135],"fewer":[136],"feature":[137],"extractor":[138],"parameters.":[139],"These":[140],"results":[141],"provides":[147],"structurally":[149],"robust":[150],"substitute":[151],"traditional":[153],"convolution":[154],"in":[155],"multidimensional":[156],"classification,":[159],"offering":[160],"high":[161],"parameter":[162],"efficiency":[163],"throughout":[166],"optimization":[168],"process.":[169]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-19T00:00:00"}