{"id":"https://openalex.org/W7127965534","doi":"https://doi.org/10.48550/arxiv.2602.04583","title":"PEPR: Privileged Event-based Predictive Regularization for Domain Generalization","display_name":"PEPR: Privileged Event-based Predictive Regularization for Domain Generalization","publication_year":2026,"publication_date":"2026-02-04","ids":{"openalex":"https://openalex.org/W7127965534","doi":"https://doi.org/10.48550/arxiv.2602.04583"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.04583","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114415112","display_name":"Gabriele Magrini","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Magrini, Gabriele","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065891142","display_name":"Federico Becattini","orcid":"https://orcid.org/0000-0003-2537-2700"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Becattini, Federico","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125147097","display_name":"Niccol\u00f2 Biondi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biondi, Niccol\u00f2","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125197314","display_name":"Pietro Pala","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pala, Pietro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.689300000667572,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.689300000667572,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.1459999978542328,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.021900000050663948,"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/rgb-color-model","display_name":"RGB color model","score":0.6736000180244446},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.628000020980835},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5429999828338623},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5099999904632568},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5023000240325928},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.40450000762939453},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.39750000834465027},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3935999870300293},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.375900000333786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.753600001335144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7170000076293945},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6736000180244446},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.628000020980835},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5429999828338623},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5099999904632568},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5023000240325928},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4839000105857849},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.39750000834465027},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3693000078201294},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35519999265670776},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3005000054836273},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.273499995470047}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.04583","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},{"id":"doi:10.48550/arxiv.2602.04583","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.04583","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":"pmh:doi:10.48550/arxiv.2602.04583","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"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":{"Deep":[0],"neural":[1],"networks":[2],"for":[3,17,47],"visual":[4],"perception":[5],"are":[6],"highly":[7],"susceptible":[8],"to":[9,105,150,169],"domain":[10,31,173],"shift,":[11],"which":[12,125],"poses":[13],"a":[14,36,49,59,129,133],"critical":[15],"challenge":[16],"real-world":[18],"deployment":[19],"under":[20,39],"conditions":[21],"that":[22],"differ":[23],"from":[24],"the":[25,40,74,83,102,107,145],"training":[26,48],"data.":[27],"To":[28,115],"address":[29],"this":[30],"generalization":[32],"challenge,":[33],"we":[34,118,143],"propose":[35],"cross-modal":[37,141],"framework":[38],"learning":[41],"using":[42],"privileged":[43,62],"information":[44],"(LUPI)":[45],"paradigm":[46],"robust,":[50],"single-modality":[51],"RGB":[52,75,103,146,164],"model.":[53],"We":[54],"leverage":[55],"event":[56,84,109],"cameras":[57],"as":[58,99,128],"source":[60],"of":[61,138],"information,":[63],"available":[64],"only":[65],"during":[66],"training.":[67],"The":[68,161],"two":[69],"modalities":[70],"exhibit":[71],"complementary":[72],"characteristics:":[73],"stream":[76,85],"is":[77,86,96],"semantically":[78],"dense":[79],"but":[80],"domain-dependent,":[81],"whereas":[82],"sparse":[87,108],"yet":[88],"more":[89],"domain-invariant.":[90],"Direct":[91],"feature":[92],"alignment":[93],"between":[94],"them":[95],"therefore":[97],"suboptimal,":[98],"it":[100],"forces":[101],"encoder":[104,147],"mimic":[106],"representation,":[110],"thereby":[111],"losing":[112],"semantic":[113,159,182],"detail.":[114],"overcome":[116],"this,":[117],"introduce":[119],"Privileged":[120],"Event-based":[121],"Predictive":[122],"Regularization":[123],"(PEPR),":[124],"reframes":[126],"LUPI":[127],"predictive":[130],"problem":[131],"in":[132],"shared":[134],"latent":[135,153],"space.":[136],"Instead":[137],"enforcing":[139],"direct":[140],"alignment,":[142],"train":[144],"with":[148],"PEPR":[149],"predict":[151],"event-based":[152],"features,":[154],"distilling":[155],"robustness":[156,168],"without":[157],"sacrificing":[158],"richness.":[160],"resulting":[162],"standalone":[163],"model":[165],"consistently":[166],"improves":[167],"day-to-night":[170],"and":[171,181],"other":[172],"shifts,":[174],"outperforming":[175],"alignment-based":[176],"baselines":[177],"across":[178],"object":[179],"detection":[180],"segmentation.":[183]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-07T00:00:00"}