{"id":"https://openalex.org/W7147345906","doi":"https://doi.org/10.48550/arxiv.2603.29941","title":"Better than Average: Spatially-Aware Aggregation of Segmentation Uncertainty Improves Downstream Performance","display_name":"Better than Average: Spatially-Aware Aggregation of Segmentation Uncertainty Improves Downstream Performance","publication_year":2026,"publication_date":"2026-03-31","ids":{"openalex":"https://openalex.org/W7147345906","doi":"https://doi.org/10.48550/arxiv.2603.29941"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.29941","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29941","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.29941","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075514856","display_name":"Vanessa Emanuela Guarino","orcid":"https://orcid.org/0000-0003-1625-4323"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Guarino, Vanessa Emanuela","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034938064","display_name":"Claudia Winklmayr","orcid":"https://orcid.org/0000-0002-8784-2301"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Winklmayr, Claudia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002413797","display_name":"Jannik Franzen","orcid":"https://orcid.org/0000-0002-0761-641X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Franzen, Jannik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056198385","display_name":"Josef Lorenz Rumberger","orcid":"https://orcid.org/0000-0002-7225-7011"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rumberger, Josef Lorenz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078706720","display_name":"Manuel Pfeuffer","orcid":"https://orcid.org/0000-0002-9308-0470"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pfeuffer, Manuel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132636654","display_name":"Sonja Greven","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Greven, Sonja","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132727595","display_name":"Klaus Maier-Hein","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maier-Hein, Klaus","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084479198","display_name":"Carsten T. L\u00fcth","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"L\u00fcth, Carsten T.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132653620","display_name":"Christoph Karg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karg, Christoph","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050629823","display_name":"Dagmar Kainmueller","orcid":"https://orcid.org/0000-0002-9830-2415"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kainmueller, Dagmar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5075514856"],"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.8998000025749207,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.8998000025749207,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.02759999968111515,"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":0.020400000736117363,"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/downstream","display_name":"Downstream (manufacturing)","score":0.7069000005722046},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7023000121116638},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6277999877929688},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.6258999705314636},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5712000131607056},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.385699987411499},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.38179999589920044},{"id":"https://openalex.org/keywords/data-aggregator","display_name":"Data aggregator","score":0.3598000109195709}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7325999736785889},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.7069000005722046},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7023000121116638},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6277999877929688},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6258999705314636},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5712000131607056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49970000982284546},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49630001187324524},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4223000109195709},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.38179999589920044},{"id":"https://openalex.org/C82578977","wikidata":"https://www.wikidata.org/wiki/Q16773055","display_name":"Data aggregator","level":3,"score":0.3598000109195709},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C191172861","wikidata":"https://www.wikidata.org/wiki/Q7899321","display_name":"Upstream (networking)","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2556999921798706},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.29941","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29941","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":"doi:10.48550/arxiv.2603.29941","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29941","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":"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":{"Uncertainty":[0],"Quantification":[1],"(UQ)":[2],"is":[3,68],"crucial":[4],"for":[5,37,77],"ensuring":[6],"the":[7,69,165],"reliability":[8],"of":[9,49,82,117,167],"automated":[10],"image":[11,18,145],"segmentations":[12],"in":[13,144,159],"safety-critical":[14],"domains":[15],"like":[16,40,86],"biomedical":[17],"analysis":[19],"or":[20,43],"autonomous":[21],"driving.":[22],"In":[23],"segmentation,":[24],"UQ":[25],"generates":[26],"pixel-wise":[27],"uncertainty":[28,127],"scores":[29,36],"that":[30,124,142,151,181],"must":[31],"be":[32],"aggregated":[33],"into":[34],"image-level":[35],"downstream":[38,57,161],"tasks":[39,162],"Out-of-Distribution":[41],"(OoD)":[42],"failure":[44,137],"detection.":[45],"Despite":[46],"routine":[47],"use":[48],"aggregation":[50],"strategies,":[51],"their":[52,132],"properties":[53],"and":[54,79,89,101,115,129,136,147,185],"impact":[55],"on":[56,134,172],"task":[58],"performance":[59,133,158,166],"have":[60],"not":[61,75],"yet":[62,72],"been":[63],"comprehensively":[64],"studied.":[65,163],"Global":[66],"Average":[67],"default":[70],"choice,":[71],"it":[73],"does":[74],"account":[76],"spatial":[78,126,154],"structural":[80],"features":[81],"segmentation":[83],"uncertainty.":[84],"Alternatives":[85],"patch-,":[87],"class-":[88],"threshold-based":[90],"strategies":[91,123],"exist,":[92],"but":[93],"lack":[94],"systematic":[95],"comparison,":[96],"leading":[97],"to":[98],"inconsistent":[99],"reporting":[100],"unclear":[102],"best":[103],"practices.":[104],"We":[105,149],"address":[106],"this":[107],"gap":[108],"by":[109],"(1)":[110],"formally":[111],"analyzing":[112],"properties,":[113],"limitations,":[114],"pitfalls":[116],"common":[118],"strategies;":[119],"(2)":[120],"proposing":[121],"novel":[122],"incorporate":[125],"structure":[128,155],"(3)":[130],"benchmarking":[131],"OoD":[135],"detection":[138],"across":[139,188],"ten":[140],"datasets":[141],"vary":[143],"geometry":[146],"structure.":[148],"find":[150],"aggregators":[152,169,184],"leveraging":[153],"yield":[156],"stronger":[157],"both":[160],"However,":[164],"individual":[168],"depends":[170],"heavily":[171],"dataset":[173],"characteristics,":[174],"so":[175],"we":[176],"(4)":[177],"propose":[178],"a":[179],"meta-aggregator":[180],"integrates":[182],"multiple":[183],"performs":[186],"robustly":[187],"datasets.":[189]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-04-02T00:00:00"}