{"id":"https://openalex.org/W7156963935","doi":"https://doi.org/10.48550/arxiv.2604.23375","title":"Hierarchical Spatio-Channel Clustering for Efficient Model Compression in Medical Image Analysis","display_name":"Hierarchical Spatio-Channel Clustering for Efficient Model Compression in Medical Image Analysis","publication_year":2026,"publication_date":"2026-04-25","ids":{"openalex":"https://openalex.org/W7156963935","doi":"https://doi.org/10.48550/arxiv.2604.23375"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.23375","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23375","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.23375","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078520052","display_name":"Sisipho Hamlomo","orcid":"https://orcid.org/0000-0003-0744-8433"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hamlomo, Sisipho","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134801586","display_name":"Marcellin Atemkeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atemkeng, Marcellin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102879092","display_name":"Habte Tadesse Likassa","orcid":"https://orcid.org/0000-0002-9334-8588"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Likassa, Habte Tadesse","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134816986","display_name":"Blaise Ravelo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ravelo, Blaise","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046143134","display_name":"Thierry Bouwmans","orcid":"https://orcid.org/0000-0003-4018-8856"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bouwmans, Thierry","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134791983","display_name":"S\u00e9bastien Lall\u00e9ch\u00e8re","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lall\u00e9ch\u00e8re, S\u00e9bastien","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070742303","display_name":"Antoine Vacavant","orcid":"https://orcid.org/0000-0001-9616-3282"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vacavant, Antoine","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134768267","display_name":"Ding-Geng Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Ding-Geng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5078520052"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.5214999914169312,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.5214999914169312,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.05829999968409538,"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/T10862","display_name":"AI in cancer detection","score":0.05119999870657921,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7473999857902527},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5759000182151794},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5659000277519226},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.54339998960495},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.45159998536109924},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4239000082015991},{"id":"https://openalex.org/keywords/set-partitioning-in-hierarchical-trees","display_name":"Set partitioning in hierarchical trees","score":0.4198000133037567},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4180999994277954},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.40299999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7583000063896179},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7473999857902527},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5759000182151794},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5659000277519226},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.54339998960495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5037999749183655},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43799999356269836},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C136968285","wikidata":"https://www.wikidata.org/wiki/Q3246374","display_name":"Set partitioning in hierarchical trees","level":5,"score":0.4198000133037567},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.40299999713897705},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.3449000120162964},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.27570000290870667},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C42704193","wikidata":"https://www.wikidata.org/wiki/Q7851097","display_name":"Tucker decomposition","level":4,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.23375","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23375","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.23375","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23375","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.4898494482040405}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"have":[4],"become":[5],"increasingly":[6],"difficult":[7],"to":[8,14,97,109,149,164],"deploy":[9],"in":[10],"resource-constrained":[11],"environments":[12],"due":[13],"their":[15,98],"large":[16],"memory":[17],"and":[18,34,38,68,104,126,131,136,158,173,199],"computational":[19],"requirements.":[20],"Although":[21],"low-rank":[22,57],"compression":[23,58,138,198],"methods":[24],"can":[25],"reduce":[26],"this":[27],"burden,":[28],"most":[29],"existing":[30],"approaches":[31],"compress":[32],"spatial":[33,66,91],"channel":[35,69],"redundancy":[36,64],"independently":[37],"therefore":[39],"do":[40],"not":[41],"fully":[42],"exploit":[43],"the":[44,83,170,187,195],"localised":[45],"structure":[46],"within":[47,101],"convolutional":[48],"feature":[49,88],"maps.":[50],"This":[51],"paper":[52],"proposes":[53],"a":[54,76,154],"hierarchical":[55],"spatio-channel":[56,112],"framework":[59,188],"for":[60,216],"CNNs":[61],"that":[62,186],"exploits":[63],"across":[65,79],"regions":[67],"activations.":[70],"Unlike":[71],"conventional":[72],"methods,":[73],"which":[74],"apply":[75],"uniform":[77],"decomposition":[78,133],"an":[80,119],"entire":[81],"layer,":[82],"proposed":[84],"approach":[85],"first":[86],"partitions":[87],"maps":[89],"into":[90],"regions,":[92],"then":[93],"groups":[94],"channels":[95],"according":[96],"co-activation":[99],"patterns":[100],"each":[102,110],"region,":[103],"finally":[105],"applies":[106],"rank-adaptive":[107],"SVD":[108,130],"resulting":[111],"cluster.":[113],"The":[114,166],"method":[115,141,167],"is":[116],"evaluated":[117],"on":[118,175],"AlexNet-based":[120],"brain":[121],"tumour":[122],"MRI":[123],"classification":[124,160,218],"model":[125],"compared":[127],"with":[128,204],"Global":[129],"Tucker":[132],"under":[134],"\\(3\\times\\)":[135],"\\(6\\times\\)":[137],"budgets.":[139],"Our":[140],"outperforms":[142],"both":[143],"baselines,":[144],"reducing":[145],"FLOPs":[146],"from":[147,162],"\\(8.21\\,\\mathrm{G}\\)":[148],"\\(1.55\\,\\mathrm{G}\\)":[150],"(\\(81.1\\%\\)":[151],"reduction),":[152],"achieving":[153],"\\(1.38\\times\\)":[155],"inference":[156],"speed-up,":[157],"increasing":[159],"accuracy":[161],"\\(87.76\\%\\)":[163],"\\(89.80\\%\\).":[165],"also":[168],"improves":[169],"macro":[171],"\\(F_1\\)-score":[172],"performance":[174],"challenging":[176],"classes":[177],"such":[178],"as":[179],"meningioma.":[180],"A":[181],"hyper-parameter":[182],"trade-off":[183],"analysis":[184],"demonstrates":[185],"provides":[189],"Pareto-optimal":[190],"configurations,":[191],"enabling":[192],"control":[193],"over":[194],"balance":[196],"between":[197],"predictive":[200],"performance.":[201],"Moderate":[202],"clustering":[203],"adaptive":[205],"rank":[206],"selection":[207],"yields":[208],"strong":[209],"results.":[210],"Bootstrap":[211],"standard":[212],"errors":[213],"are":[214],"reported":[215],"all":[217],"metrics.":[219]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-04-29T00:00:00"}