{"id":"https://openalex.org/W7161990867","doi":"https://doi.org/10.48550/arxiv.2605.20538","title":"Continual Segmentation under Joint Nonstationarity","display_name":"Continual Segmentation under Joint Nonstationarity","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7161990867","doi":"https://doi.org/10.48550/arxiv.2605.20538"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.20538","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20538","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.2605.20538","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136667299","display_name":"Prashant Pandey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pandey, Prashant","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136690657","display_name":"Himanshu Kumar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kumar, Himanshu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136679438","display_name":"Devineni Sri Venkatraya Chowdary","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chowdary, Devineni Sri Venkatraya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136674696","display_name":"Brejesh Lall","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lall, Brejesh","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.8410999774932861,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.8410999774932861,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.07599999755620956,"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":0.01889999955892563,"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/overfitting","display_name":"Overfitting","score":0.7879999876022339},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7006999850273132},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.659600019454956},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5087000131607056},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4571000039577484},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.4212999939918518},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.3790999948978424},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3513000011444092}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7879999876022339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7419000267982483},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7006999850273132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6675999760627747},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.659600019454956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6402999758720398},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5087000131607056},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.4212999939918518},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3513000011444092},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C60777511","wikidata":"https://www.wikidata.org/wiki/Q3045002","display_name":"Concept drift","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26179999113082886},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.259799987077713}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.20538","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20538","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.2605.20538","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20538","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Evolving":[0],"data":[1,106],"streams":[2],"induce":[3],"joint":[4,119,130],"nonstationarity":[5,131],"in":[6,33,43,59,132,150,174],"continual":[7,35,47,133,163],"semantic":[8,11],"segmentation,":[9],"where":[10],"classes,":[12],"input":[13],"distributions,":[14],"and":[15,53,56,67,74,110,121,141,166],"supervision":[16,79,114],"availability":[17],"change":[18],"simultaneously":[19],"over":[20,147],"time.":[21],"This":[22],"setting":[23],"reflects":[24],"practical":[25],"structured":[26,152],"prediction":[27,62,153],"systems,":[28],"yet":[29],"remains":[30],"largely":[31],"unexplored":[32],"prior":[34,148],"learning":[36,58,109,128,170],"work,":[37],"which":[38],"typically":[39],"studies":[40],"these":[41,125],"factors":[42],"isolation.":[44],"We":[45,102],"formalize":[46],"segmentation":[48,164],"under":[49,80,129],"coupled":[50],"class,":[51],"domain,":[52],"label":[54],"shifts":[55],"investigate":[57],"heterogeneous":[60,151],"dense":[61,172],"environments":[63],"with":[64],"limited":[65],"annotations":[66],"abundant":[68],"unlabeled":[69,105],"data.":[70],"To":[71],"address":[72],"instability":[73],"overfitting":[75],"arising":[76],"from":[77],"few-shot":[78,142],"distribution":[81],"drift,":[82],"we":[83],"introduce":[84,111],"gradient-adaptive":[85],"stabilization,":[86],"a":[87,98],"parameter-wise":[88],"regularization":[89],"mechanism":[90],"implemented":[91],"via":[92,118],"gradient-scaled":[93],"stochastic":[94],"perturbations":[95],"that":[96,115],"promotes":[97],"principled":[99],"stability-plasticity":[100],"tradeoff.":[101],"further":[103],"leverage":[104],"through":[107],"semi-supervised":[108],"prototype":[112,122],"anchored":[113],"validates":[116],"pseudo-labels":[117],"confidence":[120],"consistency.":[123],"Together,":[124],"mechanisms":[126],"enable":[127],"segmentation.":[134],"Extensive":[135],"empirical":[136],"evaluation":[137],"across":[138],"class-incremental,":[139],"domain-incremental,":[140],"regimes":[143],"demonstrates":[144],"consistent":[145],"improvements":[146],"methods":[149],"settings.":[154],"Our":[155],"results":[156],"expose":[157],"fundamental":[158],"failure":[159],"modes":[160],"of":[161],"existing":[162],"approaches":[165],"provide":[167],"insight":[168],"into":[169],"robust":[171],"predictors":[173],"dynamically":[175],"evolving":[176],"environments.":[177]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-22T00:00:00"}