{"id":"https://openalex.org/W7162453453","doi":"https://doi.org/10.48550/arxiv.2605.25299","title":"A Principled Self-Referenced Early Stopping Approach for Deep Image Prior","display_name":"A Principled Self-Referenced Early Stopping Approach for Deep Image Prior","publication_year":2026,"publication_date":"2026-05-24","ids":{"openalex":"https://openalex.org/W7162453453","doi":"https://doi.org/10.48550/arxiv.2605.25299"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.25299","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25299","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.2605.25299","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137001056","display_name":"Chaoyan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Chaoyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113429338","display_name":"Cheng-Han Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Cheng-Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003538946","display_name":"Ismail Alkhouri","orcid":"https://orcid.org/0000-0002-5754-5509"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alkhouri, Ismail R.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137042168","display_name":"Rongrong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Rongrong","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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.8331999778747559,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.8331999778747559,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.050700001418590546,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.03830000013113022,"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/overfitting","display_name":"Overfitting","score":0.9315999746322632},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6696000099182129},{"id":"https://openalex.org/keywords/early-stopping","display_name":"Early stopping","score":0.652999997138977},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6470999717712402},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5565999746322632},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5141000151634216},{"id":"https://openalex.org/keywords/image-restoration","display_name":"Image restoration","score":0.46939998865127563},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4602999985218048},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4375999867916107}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9315999746322632},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6696000099182129},{"id":"https://openalex.org/C5465570","wikidata":"https://www.wikidata.org/wiki/Q5326898","display_name":"Early stopping","level":3,"score":0.652999997138977},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6470999717712402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6431000232696533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6182000041007996},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5565999746322632},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5141000151634216},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.46939998865127563},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4602999985218048},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4375999867916107},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4059000015258789},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3887999951839447},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C99888217","wikidata":"https://www.wikidata.org/wiki/Q1288707","display_name":"Stopping time","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3398999869823456},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.3197000026702881},{"id":"https://openalex.org/C112633086","wikidata":"https://www.wikidata.org/wiki/Q381287","display_name":"White noise","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2897999882698059},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C2986577269","wikidata":"https://www.wikidata.org/wiki/Q11306265","display_name":"Random noise","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2718000113964081},{"id":"https://openalex.org/C35772409","wikidata":"https://www.wikidata.org/wiki/Q1323086","display_name":"Image noise","level":3,"score":0.2709999978542328},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.26510000228881836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.25299","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25299","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.2605.25299","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25299","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"Deep":[1],"Image":[2],"Prior":[3],"(DIP)":[4],"has":[5],"demonstrated":[6],"strong":[7],"capabilities":[8],"for":[9],"solving":[10],"inverse":[11],"imaging":[12],"problems":[13],"(IIPs)":[14],"by":[15,102,136],"optimizing":[16],"a":[17,24],"randomly":[18],"initialized":[19],"convolutional":[20],"neural":[21],"network":[22,37,57],"in":[23,51,63,127],"training-data-free":[25],"regime.":[26],"However,":[27,62],"DIP":[28,84,175],"suffers":[29],"from":[30,154],"overfitting":[31,117],"to":[32,36,59,72,158],"noisy":[33,93],"measurements":[34],"due":[35],"over-parameterization,":[38],"making":[39],"early":[40,85,176],"stopping":[41,86,177],"(ES)":[42],"essential.":[43],"The":[44],"most":[45],"successful":[46],"ES":[47],"method":[48],"tracks":[49],"fluctuations":[50,67],"the":[52,56,96,145,186],"running":[53],"variance":[54],"of":[55,95,147,185],"output":[58],"detect":[60],"overfitting.":[61],"many":[64],"applications,":[65],"these":[66],"may":[68],"appear":[69],"prematurely,":[70],"leading":[71],"unstable":[73],"reconstructions.":[74],"In":[75],"this":[76,103],"paper,":[77],"we":[78,114],"first":[79],"show":[80],"that":[81],"nearly":[82],"optimal":[83],"can":[87],"be":[88],"achieved":[89],"when":[90],"two":[91,108],"independent":[92,110],"copies":[94,111],"degraded":[97],"image":[98,156,160],"are":[99],"available.":[100],"Motivated":[101],"observation,":[104],"and":[105,144,162,167],"since":[106],"obtaining":[107],"fully":[109],"is":[112,133],"infeasible,":[113],"propose":[115],"an":[116,182],"detection":[118],"framework":[119],"based":[120],"on":[121,139],"constructing":[122],"pseudo":[123],"self-referenced":[124],"images,":[125],"resulting":[126],"three":[128],"IIP-specific":[129],"algorithms.":[130],"Our":[131],"approach":[132],"further":[134],"supported":[135],"theoretical":[137],"results":[138],"single-reference":[140],"validation,":[141],"pseudo-validation":[142],"estimation,":[143],"impact":[146],"shared":[148],"noise.":[149],"Across":[150],"different":[151],"IIPs,":[152],"ranging":[153],"natural":[155],"restoration":[157],"medical":[159],"reconstruction,":[161],"under":[163],"varying":[164],"noise":[165,168,187],"levels":[166],"types,":[169],"our":[170],"methods":[171],"consistently":[172],"outperform":[173],"existing":[174],"approaches,":[178],"all":[179],"without":[180],"requiring":[181],"accurate":[183],"estimate":[184],"level.":[188]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-27T00:00:00"}