{"id":"https://openalex.org/W7166539727","doi":"https://doi.org/10.48550/arxiv.2606.28268","title":"Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation","display_name":"Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation","publication_year":2026,"publication_date":"2026-06-26","ids":{"openalex":"https://openalex.org/W7166539727","doi":"https://doi.org/10.48550/arxiv.2606.28268"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.28268","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.28268","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":null,"license_id":null,"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.2606.28268","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139616020","display_name":"Ali Zia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zia, Ali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139570993","display_name":"Usman Ali","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali, Usman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139576909","display_name":"Abdul Rehman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rehman, Abdul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115647644","display_name":"Umer Ramzan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramzan, Umer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139571094","display_name":"Kang Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077625866","display_name":"Muhammad Faheem","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Faheem, Muhammad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128765994","display_name":"Shahnawaz Qureshi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qureshi, Shahnawaz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139597337","display_name":"Wei Xiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang, Wei","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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0013000000035390258,"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":0.000699999975040555,"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/segmentation","display_name":"Segmentation","score":0.6625000238418579},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6342999935150146},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5778999924659729},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.5543000102043152},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.3880000114440918},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3659999966621399},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.34880000352859497},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3443000018596649},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.32269999384880066}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6995000243186951},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6625000238418579},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6342999935150146},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5778999924659729},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.5543000102043152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5325999855995178},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.34880000352859497},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3443000018596649},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.3181999921798706},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2858999967575073},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2685999870300293},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.2533999979496002},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.25040000677108765},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.28268","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.28268","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.28268","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.28268","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":null,"license_id":null,"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":{"Test-time":[0],"adaptation":[1,201],"(TTA)":[2],"has":[3],"emerged":[4],"as":[5,32,55],"a":[6,75,82,117,203],"promising":[7],"paradigm":[8],"for":[9,20,137],"mitigating":[10],"distribution":[11],"shifts":[12],"in":[13],"deep":[14],"models.":[15],"However,":[16],"existing":[17],"TTA":[18,90],"approaches":[19],"anomaly":[21,53,107,175],"segmentation":[22,122,178],"remain":[23],"limited":[24],"by":[25],"their":[26],"reliance":[27,132],"on":[28,133,184],"pixel-level":[29],"heuristics,":[30],"such":[31],"confidence":[33],"thresholding":[34,136],"or":[35,189],"entropy":[36],"minimisation,":[37],"which":[38],"fail":[39],"to":[40,92,106,206],"preserve":[41],"structural":[42,96,190],"consistency":[43],"under":[44],"noise":[45],"and":[46,95,142,147,163,177,215],"texture":[47],"variation.":[48],"Moreover,":[49],"they":[50],"typically":[51],"treat":[52],"maps":[54],"flat":[56],"intensity":[57],"fields,":[58],"ignoring":[59],"the":[60,89,126,181,210],"higher-order":[61],"spatial":[62],"relationships":[63],"that":[64,78,115,195],"characterise":[65],"complex":[66,104,187],"defect":[67],"geometries.":[68],"We":[69],"introduce":[70],"TopoTTA":[71,110],"(Topological":[72],"Test-Time":[73],"Adaptation),":[74],"novel":[76],"framework":[77],"integrates":[79],"persistent":[80],"homology,":[81],"tool":[83],"from":[84],"topological":[85,113,197],"data":[86],"analysis,":[87],"into":[88,199],"pipeline":[91],"enforce":[93],"geometric":[94,188,213],"coherence":[97],"during":[98],"adaptation.":[99,217],"By":[100],"applying":[101],"multi-level":[102],"cubical":[103],"filtration":[105],"score":[108],"maps,":[109],"derives":[111],"robust":[112,216],"pseudo-labels":[114],"guide":[116],"lightweight":[118],"test-time":[119,200],"classifier,":[120],"enhancing":[121],"quality":[123],"without":[124],"retraining":[125],"backbone":[127],"model.":[128],"The":[129],"approach":[130],"avoids":[131],"method-specific":[134],"raw-score":[135],"mask":[138],"binarisation,":[139],"preserves":[140],"connectivity,":[141],"generalises":[143],"across":[144,152],"both":[145],"2D":[146],"3D":[148],"modalities.":[149],"Extensive":[150],"experiments":[151],"six":[153],"standard":[154],"benchmarks":[155],"(MVTec":[156],"AD,":[157],"VisA,":[158],"Real-IAD,":[159],"MVTec":[160,164],"3D-AD,":[161],"AnomalyShapeNet,":[162],"LOCO)":[165],"demonstrate":[166],"an":[167],"average":[168],"15%":[169],"F1":[170],"improvement":[171],"over":[172],"state-of-the-art":[173],"unsupervised":[174],"detection":[176],"methods,":[179],"with":[180],"largest":[182],"gains":[183],"anomalies":[185],"exhibiting":[186],"variations.":[191],"These":[192],"findings":[193],"suggest":[194],"integrating":[196],"reasoning":[198],"provides":[202],"principled":[204],"route":[205],"structure-aware":[207],"generalisation,":[208],"bridging":[209],"gap":[211],"between":[212],"learning":[214]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-30T00:00:00"}