{"id":"https://openalex.org/W7160961002","doi":"https://doi.org/10.48550/arxiv.2605.10161","title":"OUIDecay: Adaptive Layer-wise Weight Decay for CNNs Using Online Activation Patterns","display_name":"OUIDecay: Adaptive Layer-wise Weight Decay for CNNs Using Online Activation Patterns","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160961002","doi":"https://doi.org/10.48550/arxiv.2605.10161"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.10161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10161","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.10161","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135984732","display_name":"Alberto Fern\u00e1ndez-Hern\u00e1ndez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fern\u00e1ndez-Hern\u00e1ndez, Alberto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007319120","display_name":"Jose I. Mestre","orcid":"https://orcid.org/0000-0001-5954-4131"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mestre, Jose I.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124332705","display_name":"Cristian P\u00e9rez-Corral","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P\u00e9rez-Corral, Cristian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135984940","display_name":"Manuel F. Dolz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dolz, Manuel F.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040384183","display_name":"J. Duato","orcid":"https://orcid.org/0000-0002-7785-0607"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duato, Jose","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135948392","display_name":"Enrique S. Quintana-Ort\u00ed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quintana-Ort\u00ed, Enrique S.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.6011000275611877,"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":0.6011000275611877,"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":0.052799999713897705,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.04320000112056732,"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/regularization","display_name":"Regularization (linguistics)","score":0.7075999975204468},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5170999765396118},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45350000262260437},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.376800000667572},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.3578999936580658},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.35749998688697815},{"id":"https://openalex.org/keywords/adaptive-algorithm","display_name":"Adaptive algorithm","score":0.32030001282691956}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7075999975204468},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5616999864578247},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5170999765396118},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47600001096725464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4503999948501587},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3463999927043915},{"id":"https://openalex.org/C2776003309","wikidata":"https://www.wikidata.org/wiki/Q1988072","display_name":"Adaptive algorithm","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30630001425743103},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.28529998660087585},{"id":"https://openalex.org/C102248274","wikidata":"https://www.wikidata.org/wiki/Q168388","display_name":"Adaptive filter","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.10161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10161","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.10161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10161","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":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Weight":[0],"decay":[1,63,107,119,174,184],"remains":[2],"one":[3],"of":[4,91,98,164],"the":[5,69,95,110,114,157,191],"most":[6],"widely":[7],"used":[8],"regularization":[9,49,83],"mechanisms":[10],"for":[11,65,196],"training":[12],"convolutional":[13],"neural":[14],"networks,":[15],"yet":[16],"it":[17],"is":[18,176],"still":[19],"commonly":[20],"applied":[21],"as":[22],"a":[23,87,177],"fixed":[24,183],"coefficient":[25],"shared":[26],"by":[27,68],"all":[28],"layers":[29,38,112],"throughout":[30],"training.":[31],"This":[32],"uniform":[33],"treatment":[34],"ignores":[35],"that":[36,154,171],"different":[37,41,48],"may":[39,46],"follow":[40],"structural":[42,96],"dynamics":[43],"and":[44,60,102,131,149,179,185,194],"therefore":[45],"require":[47,134],"strengths.":[50],"In":[51],"this":[52],"work,":[53],"we":[54],"propose":[55],"OUIDecay,":[56],"an":[57,73],"adaptive":[58,118,187],"layer-wise":[59],"time-dependent":[61],"weight":[62,106,173],"scheduler":[64],"CNNs":[66],"driven":[67],"Overfitting-Underfitting":[70],"Indicator":[71],"(OUI),":[72],"activation-based":[74],"metric":[75],"previously":[76],"shown":[77],"to":[78,93,109,182],"provide":[79],"early":[80],"information":[81,126],"about":[82],"quality.":[84],"OUIDecay":[85,155],"uses":[86],"lightweight":[88,193],"batch-based":[89],"formulation":[90],"OUI":[92],"monitor":[94],"behavior":[97],"each":[99],"layer":[100],"online":[101,197],"periodically":[103],"rescales":[104],"its":[105],"relative":[108],"other":[111],"in":[113,161],"network.":[115],"Unlike":[116],"gradient-based":[117,186],"methods,":[120],"our":[121],"approach":[122],"relies":[123],"on":[124,138],"functional":[125],"extracted":[127],"from":[128],"activation":[129],"patterns":[130],"does":[132],"not":[133],"validation":[135],"data.":[136],"Experiments":[137],"EfficientNet-B0":[139],"with":[140,144,147,151],"Stanford":[141],"Cars,":[142],"ResNet50":[143],"Food101,":[145],"DenseNet121":[146],"CIFAR100,":[148],"MobileNetV2":[150],"CIFAR10":[152],"show":[153],"achieves":[156],"best":[158],"mean":[159],"best-validation-loss":[160],"7":[162],"out":[163],"8":[165],"evaluated":[166],"settings.":[167],"These":[168],"results":[169],"indicate":[170],"activation-driven":[172],"adaptation":[175],"practical":[178],"effective":[180],"alternative":[181],"decay,":[188],"while":[189],"keeping":[190],"method":[192],"suitable":[195],"use.":[198]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-13T00:00:00"}