{"id":"https://openalex.org/W7162022755","doi":"https://doi.org/10.48550/arxiv.2605.21426","title":"Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks","display_name":"Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7162022755","doi":"https://doi.org/10.48550/arxiv.2605.21426"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.21426","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21426","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.2605.21426","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114176128","display_name":"Qishi Zhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhan, Qishi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136628909","display_name":"Ziheng Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Ziheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136626320","display_name":"Minxuan Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Minxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"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/T10036","display_name":"Advanced Neural Network Applications","score":0.30809998512268066,"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":0.30809998512268066,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.21250000596046448,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.13529999554157257,"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/granularity","display_name":"Granularity","score":0.724399983882904},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6035000085830688},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5702000260353088},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5605999827384949},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.4262000024318695},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.40380001068115234},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.38260000944137573},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3785000145435333}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.724399983882904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6507999897003174},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6035000085830688},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5702000260353088},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5605999827384949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4325000047683716},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3880000114440918},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C180145272","wikidata":"https://www.wikidata.org/wiki/Q7504144","display_name":"Shrinkage","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C70958404","wikidata":"https://www.wikidata.org/wiki/Q7512728","display_name":"Signal reconstruction","level":4,"score":0.31709998846054077},{"id":"https://openalex.org/C124851039","wikidata":"https://www.wikidata.org/wiki/Q2665459","display_name":"Compressed sensing","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2987000048160553},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C126691448","wikidata":"https://www.wikidata.org/wiki/Q2028919","display_name":"Magnitude (astronomy)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2694999873638153},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.21426","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21426","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.2605.21426","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21426","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"One-shot":[0],"magnitude":[1,35],"pruning":[2,15],"can":[3,40,67],"cause":[4],"severe":[5],"accuracy":[6,185],"collapse":[7],"in":[8,30,173],"the":[9,14,18,50,63,76,92,97,170],"high-sparsity":[10,174],"regime,":[11],"even":[12],"when":[13],"mask":[16],"preserves":[17],"largest":[19],"weights.":[20],"We":[21,79],"argue":[22],"that":[23,44,90,201,209],"this":[24],"failure":[25],"reflects":[26],"a":[27,59,85,103,114,143],"granularity":[28,93,98],"mismatch":[29],"post-pruning":[31,125,212],"repair.":[32,213],"Under":[33],"global":[34],"pruning,":[36],"nearly":[37],"collapsed":[38],"channels":[39,43,71,122],"coexist":[41],"with":[42,113,123,169,189],"retain":[45],"informative":[46],"activation":[47,55],"variance":[48,204],"within":[49],"same":[51],"layer.":[52],"Existing":[53],"layer-wise":[54,167,192],"repair":[56,88,95,193],"methods":[57],"apply":[58],"single":[60],"correction":[61,105],"to":[62,74,96],"whole":[64],"layer,":[65],"and":[66,110,147,156,159,194,208],"therefore":[68],"over-amplify":[69],"damaged":[70],"while":[72,127],"trying":[73],"restore":[75],"layer-level":[77],"signal.":[78],"propose":[80],"Adaptive":[81],"Signal":[82],"Resuscitation":[83],"(ASR),":[84],"training-free":[86],"channel-wise":[87,203],"method":[89],"matches":[91],"of":[94,99],"damage.":[100],"ASR":[101,137,163,181],"estimates":[102],"variance-matching":[104],"for":[106,121,130,191,196],"each":[107],"output":[108],"channel":[109],"stabilizes":[111,211],"it":[112],"data-driven":[115],"shrinkage":[116,210],"rule,":[117],"suppressing":[118],"unreliable":[119],"corrections":[120,129],"weak":[124],"signal":[126],"preserving":[128],"healthier":[131],"channels.":[132],"Applied":[133],"before":[134],"BatchNorm":[135],"recalibration,":[136],"requires":[138],"only":[139],"forward":[140],"passes":[141],"on":[142,186],"small":[144],"calibration":[145],"set":[146],"no":[148],"retraining.":[149],"Across":[150],"three":[151],"datasets,":[152],"four":[153],"convolutional":[154],"architectures,":[155],"both":[157],"unstructured":[158],"structured":[160],"sparsity":[161],"settings,":[162],"generally":[164],"improves":[165],"over":[166],"repair,":[168],"clearest":[171],"gains":[172],"regimes.":[175],"On":[176],"ResNet-50":[177],"at":[178],"90%":[179],"sparsity,":[180],"recovers":[182],"55.6%":[183],"top-1":[184],"CIFAR-10,":[187],"compared":[188],"41.0%":[190],"28.0%":[195],"BatchNorm-only":[197],"recalibration.":[198],"Ablations":[199],"show":[200],"naive":[202],"matching":[205],"is":[206],"insufficient,":[207]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-22T00:00:00"}