{"id":"https://openalex.org/W7225829415","doi":"https://doi.org/10.21203/rs.3.rs-11679740/v1","title":"Augmentation-induced sibling leakage in small-data surface imaging: measurement and a reporting protocol","display_name":"Augmentation-induced sibling leakage in small-data surface imaging: measurement and a reporting protocol","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225829415","doi":"https://doi.org/10.21203/rs.3.rs-11679740/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11679740/v1","doi":"https://doi.org/10.21203/rs.3.rs-11679740/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11679740/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21203/rs.3.rs-11679740/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159994881","display_name":"Shaoxuan Zhang","orcid":"https://orcid.org/0009-0001-4103-6099","observed_orcids":["https://orcid.org/0009-0001-4103-6099"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shaoxuan Zhang","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5159994881"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.47440001368522644,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.47440001368522644,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.25119999051094055,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.1995999962091446,"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":[],"concepts":[{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.6208000183105469},{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.5737000107765198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5324000120162964},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49480000138282776},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.48660001158714294},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4771000146865845},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.46779999136924744},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.41200000047683716},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.37950000166893005},{"id":"https://openalex.org/C178518018","wikidata":"https://www.wikidata.org/wiki/Q1024555","display_name":"CUSUM","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.34790000319480896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3465000092983246},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3449999988079071},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.298799991607666},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.2854999899864197},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C2983696493","wikidata":"https://www.wikidata.org/wiki/Q7705730","display_name":"Test site","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C148837635","wikidata":"https://www.wikidata.org/wiki/Q1742397","display_name":"Sawtooth wave","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25619998574256897},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.25440001487731934},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11679740/v1","doi":"https://doi.org/10.21203/rs.3.rs-11679740/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11679740/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11679740/v1","doi":"https://doi.org/10.21203/rs.3.rs-11679740/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11679740/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Deep":[1],"learning":[2],"papers":[3],"on":[4,84,123],"surface":[5],"and":[6,26,45,63,88,96,118,181,190],"microscopy":[7,102],"imaging":[8],"routinely":[9],"build":[10],"their":[11],"training":[12,43,70],"sets":[13],"by":[14,81,110,119,130],"augmenting":[15],"a":[16,39,74,79,104,145,177,182],"handful":[17],"of":[18,24,68,167,172],"acquisitions":[19,160],"into":[20],"hundreds":[21],"or":[22],"thousands":[23],"images,":[25,71],"then":[27,37],"split":[28,76,80,138],"the":[29,42,46,56,59,66,69,124,133,136,149,154,165,170],"augmented":[30],"pool":[31],"at":[32,112,121],"random.":[33],"Every":[34],"test":[35,150],"image":[36],"has":[38],"near-copy":[40],"in":[41,99],"set,":[44],"reported":[47],"metric":[48],"measures":[49],"recognition":[50],"rather":[51,152],"than":[52,153],"generalisation.":[53],"We":[54,175],"quantify":[55],"cost.":[57],"Holding":[58],"annotation":[60],"budget":[61],"fixed":[62],"varying":[64],"only":[65],"provenance":[67],"we":[72,194],"compare":[73],"random":[75,137],"(A)":[77],"with":[78,93,103],"acquisition":[82],"(B)":[83],"two":[85,89,113],"public":[86],"benchmarks":[87],"tasks:":[90],"surface-defect":[91],"detection":[92],"Faster":[94],"R-CNN,":[95],"point-defect":[97],"segmentation":[98],"scanning":[100],"tunnelling":[101],"U-Net.":[105],"Random":[106],"splitting":[107],"overstates":[108,128],"mAP@0.5:0.95":[109],"0.546":[111],"source":[114],"images":[115],"per":[116],"class":[117],"0.303":[120],"ten;":[122],"STM":[125],"data":[126],"it":[127],"Dice":[129],"0.278--0.448.":[131],"At":[132],"smallest":[134],"budgets":[135],"drives":[139],"mAP@0.5":[140],"to":[141,188],"1.000":[142],"$\\pm$":[143],"0.000,":[144],"number":[146],"that":[147,185],"describes":[148],"set":[151],"model.":[155],"The":[156],"gap":[157],"narrows":[158],"as":[159],"increase;":[161],"what":[162],"declines":[163],"is":[164],"benefit":[166],"leaking,":[168],"not":[169],"quality":[171],"grouped":[173],"evaluation.":[174],"propose":[176],"four-item":[178],"reporting":[179],"protocol":[180],"sibling-leakage":[183],"statistic":[184],"costs":[186],"seconds":[187],"compute":[189],"whose":[191],"error":[192],"behaviour":[193],"characterise.":[195]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}