{"id":"https://openalex.org/W7162671804","doi":"https://doi.org/10.48550/arxiv.2605.27962","title":"Bridging the Generalization Gap in Adverse Weather Segmentation: A Training Recipe Perspective","display_name":"Bridging the Generalization Gap in Adverse Weather Segmentation: A Training Recipe Perspective","publication_year":2026,"publication_date":"2026-05-27","ids":{"openalex":"https://openalex.org/W7162671804","doi":"https://doi.org/10.48550/arxiv.2605.27962"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.27962","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27962","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.27962","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137290334","display_name":"Cong Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Cong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102245902","display_name":"Pu Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Pu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137259117","display_name":"Yumei Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yumei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5120978842","display_name":"Boyou Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Boyou","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":0.3880999982357025,"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":0.3880999982357025,"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/T11019","display_name":"Image Enhancement Techniques","score":0.17239999771118164,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.10849999636411667,"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/bridging","display_name":"Bridging (networking)","score":0.8276000022888184},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6432999968528748},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6309999823570251},{"id":"https://openalex.org/keywords/recipe","display_name":"Recipe","score":0.6075000166893005},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.576200008392334},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.508899986743927},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4959000051021576},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4925000071525574}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8276000022888184},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6432999968528748},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6309999823570251},{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.6075000166893005},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.576200008392334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5227000117301941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5171999931335449},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.508899986743927},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4959000051021576},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4925000071525574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4844000041484833},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3379000127315521},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.31060001254081726},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25609999895095825},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.27962","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27962","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.27962","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27962","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":"Preprint"},"sustainable_development_goals":[{"score":0.5194768309593201,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"},{"score":0.4273313581943512,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3],"approach":[4],"for":[5,74,160],"the":[6,47,53,101,122],"8th":[7],"UG2+":[8],"Workshop":[9],"(CVPR":[10],"2026)":[11],"Track~2,":[12],"which":[13],"targets":[14],"semantic":[15],"segmentation":[16,162],"of":[17,103,131,140],"outdoor":[18],"scenes":[19],"degraded":[20],"by":[21],"five":[22],"weather":[23],"conditions:":[24],"blur,":[25],"darkness,":[26],"snow,":[27],"haze,":[28],"and":[29,111,153],"glare.":[30],"A":[31],"central":[32],"challenge":[33],"we":[34,98],"observe":[35],"is":[36,72],"a":[37,79,94,128],"severe":[38],"generalization":[39],"gap":[40,130],"--":[41,135],"models":[42],"that":[43,68,139],"perform":[44],"well":[45],"on":[46,52,121],"validation":[48,64],"set":[49,125],"often":[50],"collapse":[51],"test":[54,124],"set.":[55],"For":[56],"instance,":[57],"SegFormer-B5":[58],"drops":[59],"16.1":[60],"mIoU":[61,120],"points":[62,134],"from":[63,93,147],"to":[65,156],"test,":[66],"suggesting":[67],"model":[69,154],"capacity":[70],"alone":[71],"insufficient":[73],"robustness.":[75],"We":[76,143],"investigate":[77],"whether":[78],"carefully":[80],"designed":[81],"training":[82],"recipe,":[83],"rather":[84],"than":[85,137],"architectural":[86,148],"complexity,":[87],"can":[88],"address":[89],"this":[90],"gap.":[91],"Starting":[92],"pre-trained":[95],"SegMAN-S":[96],"backbone,":[97],"systematically":[99],"study":[100],"effects":[102],"domain-adaptive":[104],"fine-tuning,":[105],"multi-source":[106],"data":[107],"mixing,":[108],"scene-balanced":[109],"sampling,":[110],"synthetic":[112],"degradation":[113],"augmentation.":[114],"Our":[115],"final":[116],"system":[117],"achieves":[118],"59.9\\%":[119],"official":[123],"while":[126],"maintaining":[127],"validation-test":[129],"only":[132],"6.5":[133],"less":[136],"half":[138],"larger":[141],"models.":[142],"analyze":[144],"negative":[145],"results":[146],"modifications,":[149],"loss":[150],"function":[151],"variants,":[152],"scaling":[155],"provide":[157],"practical":[158],"insights":[159],"weather-robust":[161],"under":[163],"limited":[164],"data.":[165]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-29T00:00:00"}