{"id":"https://openalex.org/W4416016822","doi":"https://doi.org/10.1145/3746252.3761064","title":"SupLID: Geometrical Guidance for Out-of-Distribution Detection in Semantic Segmentation","display_name":"SupLID: Geometrical Guidance for Out-of-Distribution Detection in Semantic Segmentation","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416016822","doi":"https://doi.org/10.1145/3746252.3761064"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761064","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761064","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746252.3761064","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117075905","display_name":"Nimeshika Udayangani","orcid":"https://orcid.org/0009-0001-7823-9738"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Nimeshika Udayangani","raw_affiliation_strings":["The University of Melbourne, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0009-0001-7823-9738","affiliations":[{"raw_affiliation_string":"The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070030398","display_name":"Sarah Erfani","orcid":"https://orcid.org/0000-0003-0885-0643"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sarah Erfani","raw_affiliation_strings":["The University of Melbourne, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0885-0643","affiliations":[{"raw_affiliation_string":"The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076014464","display_name":"Christopher Leckie","orcid":"https://orcid.org/0000-0002-4388-0517"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Christopher Leckie","raw_affiliation_strings":["The University of Melbourne, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4388-0517","affiliations":[{"raw_affiliation_string":"The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165779595"],"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":"2905","last_page":"2914"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.7531999945640564,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.7531999945640564,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.17149999737739563,"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":0.016100000590085983,"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/segmentation","display_name":"Segmentation","score":0.7433000206947327},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6248999834060669},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5386000275611877},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.492000013589859},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.47620001435279846},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4366999864578247},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41370001435279846},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.37770000100135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534999847412109},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7433000206947327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6668999791145325},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6248999834060669},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5386000275611877},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.492000013589859},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4366999864578247},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3889999985694885},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3357999920845032},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3262999951839447},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.26499998569488525},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746252.3761064","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761064","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.18816","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.18816","pdf_url":"https://arxiv.org/pdf/2511.18816","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3746252.3761064","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761064","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1292147475","display_name":null,"funder_award_id":"LE170100200,DE220100680","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1969967031","https://openalex.org/W1970647353","https://openalex.org/W2039797405","https://openalex.org/W2118246710","https://openalex.org/W2169036209","https://openalex.org/W2247953682","https://openalex.org/W2758659144","https://openalex.org/W2894824251","https://openalex.org/W2933610837","https://openalex.org/W3011680720","https://openalex.org/W3196292572","https://openalex.org/W4394717471"],"related_works":[],"abstract_inverted_index":{"Out-of-Distribution":[0],"(OOD)":[1],"detection":[2],"in":[3],"semantic":[4,90,196],"segmentation":[5,197],"aims":[6],"to":[7,21,65,170,178],"localize":[8],"anomalous":[9],"regions":[10],"at":[11,115,144,199,228],"the":[12,35,84,88,102,116,131,135,145,175],"pixel":[13,117],"level,":[14,147],"advancing":[15],"beyond":[16],"traditional":[17,171],"image-level":[18,40],"OOD":[19,41,80,142,181,211],"techniques":[20],"better":[22],"suit":[23],"real-world":[24],"applications":[25],"such":[26],"as":[27,166,184],"autonomous":[28],"driving.":[29],"Recent":[30],"literature":[31],"has":[32],"successfully":[33],"explored":[34],"adaptation":[36],"of":[37,61,87,105,134],"commonly":[38],"used":[39],"methods-primarily":[42],"based":[43],"on":[44],"classifier-derived":[45,79],"confidence":[46],"scores":[47,81,143],"(e.g.,":[48],"energy":[49],"or":[50],"entropy)-for":[51],"this":[52,68],"pixel-precise":[53],"task.":[54],"However,":[55],"these":[56],"methods":[57],"inherit":[58],"a":[59,73,126,167,185],"set":[60],"limitations,":[62],"including":[63,220],"vulnerability":[64],"overconfidence.":[66],"In":[67],"work,":[69],"we":[70],"introduce":[71],"SupLID,":[72],"novel":[74],"framework":[75],"that":[76,129,159,205],"effectively":[77,100],"guides":[78],"by":[82,108],"exploiting":[83],"geometrical":[85,127,160],"structure":[86,104,133],"underlying":[89],"space,":[91],"particularly":[92],"using":[93],"Linear":[94],"Intrinsic":[95],"Dimensionality":[96],"(LID).":[97],"While":[98],"LID":[99],"characterizes":[101],"local":[103],"high-dimensional":[106],"data":[107],"analyzing":[109],"distance":[110],"distributions,":[111],"its":[112],"direct":[113],"application":[114],"level":[118],"remains":[119],"challenging.":[120],"To":[121],"overcome":[122],"this,":[123],"SupLID":[124,164,189,206],"constructs":[125],"coreset":[128],"captures":[130],"intrinsic":[132],"in-distribution":[136],"(ID)":[137],"subspace.":[138],"It":[139],"then":[140],"computes":[141],"superpixel":[146],"enabling":[148],"both":[149],"efficient":[150],"real-time":[151],"inference":[152],"and":[153,223],"improved":[154],"spatial":[155],"smoothness.":[156],"We":[157],"demonstrate":[158,204],"cues":[161],"derived":[162],"from":[163],"serve":[165],"complementary":[168],"signal":[169],"classifier":[172,198],"confidence,":[173],"enhancing":[174],"model's":[176],"ability":[177],"detect":[179],"diverse":[180],"scenarios.":[182],"Designed":[183],"post-hoc":[186],"scoring":[187],"method,":[188],"can":[190],"be":[191],"seamlessly":[192],"integrated":[193],"with":[194],"any":[195],"deployment":[200],"time.":[201],"Our":[202],"results":[203],"significantly":[207],"enhances":[208],"existing":[209],"classifier-based":[210],"scores,":[212],"achieving":[213],"state-of-the-art":[214],"performance":[215],"across":[216],"key":[217],"evaluation":[218],"metrics,":[219],"AUR,":[221],"FPR,":[222],"AUP.":[224],"Code":[225],"is":[226],"available":[227],"https://github.com/hdnugit/SupLID.":[229]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}