{"id":"https://openalex.org/W7164889841","doi":"https://doi.org/10.48550/arxiv.2606.15837","title":"Learning a Sampling-Free Variational DNN Plugin from Tiny Training Sets to Refine OOD Segmentation With Uncertainty Estimation","display_name":"Learning a Sampling-Free Variational DNN Plugin from Tiny Training Sets to Refine OOD Segmentation With Uncertainty Estimation","publication_year":2026,"publication_date":"2026-06-14","ids":{"openalex":"https://openalex.org/W7164889841","doi":"https://doi.org/10.48550/arxiv.2606.15837"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.15837","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15837","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2606.15837","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138715221","display_name":"Jimut B. Pal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pal, Jimut B.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5017642893","display_name":"Suyash P. Awate","orcid":"https://orcid.org/0000-0002-4945-9539"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Awate, Suyash P.","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":0.227400004863739,"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":0.227400004863739,"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/T10862","display_name":"AI in cancer detection","score":0.10209999978542328,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.09510000050067902,"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/softmax-function","display_name":"Softmax function","score":0.7785000205039978},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7544999718666077},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5497999787330627},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5059999823570251},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4496999979019165},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43950000405311584},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.40689998865127563},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37229999899864197},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.3650999963283539},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.3546000123023987}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.7785000205039978},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7544999718666077},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7476000189781189},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6791999936103821},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5497999787330627},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5059999823570251},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4781999886035919},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4496999979019165},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43950000405311584},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.40689998865127563},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3650999963283539},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.31049999594688416},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.3091000020503998},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.30660000443458557},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.26969999074935913},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.25290000438690186},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.15837","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15837","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2606.15837","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15837","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"frequently":[4],"fail":[5],"to":[6,8,24,33,57,106,124,180],"generalize":[7],"out-of-distribution":[9],"(OOD)":[10],"medical":[11,42],"images":[12],"because":[13],"of":[14,37,83,102,151,186,191],"variations":[15],"in":[16],"scanners":[17],"and":[18,39,118,157,188,194],"acquisition":[19],"protocols.":[20],"Retraining":[21],"DNN":[22,54],"models":[23],"address":[25,45],"these":[26],"distribution":[27,82,110],"shifts":[28],"is":[29],"often":[30],"impractical":[31],"due":[32],"the":[34,103,152,174,192],"high":[35],"cost":[36],"acquiring":[38],"annotating":[40],"new":[41],"datasets.":[43,92],"To":[44],"this,":[46],"we":[47],"introduce":[48],"VarDeepPCA,":[49],"a":[50,81,100],"novel":[51,95],"lightweight":[52],"variational":[53,96],"framework":[55,98,138],"designed":[56],"restore/refine":[58],"degraded":[59],"segmentation":[60,132,150,170],"maps":[61,171],"by":[62,173,208],"leveraging":[63],"intrinsic":[64],"geometric":[65],"priors.":[66],"Unlike":[67],"existing":[68,163,175,209],"approaches":[69],"that":[70,166,206],"require":[71],"target-domain":[72],"data":[73,179,204],"or":[74],"extensive":[75],"pre-training,":[76],"our":[77,94,137],"VarDeepPCA":[78,123,167],"explicitly":[79],"learns":[80],"valid":[84],"anatomical":[85,184],"geometries":[86,187],"using":[87,144],"only":[88],"small":[89],"in-distribution":[90],"(ID)":[91],"Theoretically,":[93],"learning":[97,117],"leverages":[99],"reinterpretation":[101],"softmax":[104],"mapping":[105],"implicitly":[107],"perform":[108],"exact":[109],"modeling,":[111],"thereby":[112],"enabling":[113],"computationally":[114],"efficient,":[115],"sampling-free":[116],"inference.":[119],"This":[120],"also":[121],"enables":[122],"provide":[125],"uncertainty":[126],"estimates":[127],"associated":[128],"with":[129],"its":[130],"restored":[131],"maps.":[133],"We":[134],"empirically":[135],"validate":[136],"across":[139],"4":[140],"distinct":[141],"clinical":[142,189],"applications,":[143],"14":[145],"publicly":[146],"available":[147],"datasets,":[148],"involving":[149],"myocardium,":[153],"neuroretinal":[154],"rim,":[155],"prostate,":[156],"fetal":[158],"head.":[159],"Comparisons":[160],"against":[161],"15":[162],"methods":[164,176],"demonstrate":[165],"consistently":[168],"restores":[169],"produced":[172],"on":[177],"OOD":[178],"(i)":[181],"significantly":[182,196],"improve":[183],"plausibility":[185],"utility":[190],"segmentations,":[193],"(ii)":[195],"reduce":[197],"errors,":[198],"without":[199],"needing":[200],"any":[201],"more":[202],"training":[203],"than":[205],"used":[207],"methods.":[210]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-17T00:00:00"}