{"id":"https://openalex.org/W4416749581","doi":"https://doi.org/10.1109/iros60139.2025.11246989","title":"Leveraging Text-Driven Semantic Variation for Robust OOD Segmentation","display_name":"Leveraging Text-Driven Semantic Variation for Robust OOD Segmentation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749581","doi":"https://doi.org/10.1109/iros60139.2025.11246989"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061183744","display_name":"Seungheon Song","orcid":"https://orcid.org/0000-0001-8819-8055"},"institutions":[{"id":"https://openalex.org/I110273157","display_name":"Kookmin University","ror":"https://ror.org/0049erg63","country_code":"KR","type":"education","lineage":["https://openalex.org/I110273157"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seungheon Song","raw_affiliation_strings":["Kookmin University,College of Computer Science,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Kookmin University,College of Computer Science,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I110273157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011313652","display_name":"Jaekoo Lee","orcid":"https://orcid.org/0000-0002-5947-5487"},"institutions":[{"id":"https://openalex.org/I110273157","display_name":"Kookmin University","ror":"https://ror.org/0049erg63","country_code":"KR","type":"education","lineage":["https://openalex.org/I110273157"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaekoo Lee","raw_affiliation_strings":["Kookmin University,College of Computer Science,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Kookmin University,College of Computer Science,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I110273157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061183744"],"corresponding_institution_ids":["https://openalex.org/I110273157"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40172851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9909","last_page":"9916"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.32760000228881836,"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":0.32760000228881836,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.31610000133514404,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.10119999945163727,"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":0.7498999834060669},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5737000107765198},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4724000096321106},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.35199999809265137},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.3490000069141388},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3456000089645386}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7498999834060669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7056000232696533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5828999876976013},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5737000107765198},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4724000096321106},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.35199999809265137},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33559998869895935},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.328000009059906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2957000136375427},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2981786146","https://openalex.org/W3095892876","https://openalex.org/W3110437118","https://openalex.org/W3136793533","https://openalex.org/W3138516171","https://openalex.org/W3176640650","https://openalex.org/W3198377975","https://openalex.org/W4225896280","https://openalex.org/W4226058394","https://openalex.org/W4312310776","https://openalex.org/W4312420092","https://openalex.org/W4312601785","https://openalex.org/W4312815172","https://openalex.org/W4312933868","https://openalex.org/W4312960937","https://openalex.org/W4379116138","https://openalex.org/W4386113239","https://openalex.org/W4390872487","https://openalex.org/W4390873436","https://openalex.org/W4390874575","https://openalex.org/W4392172801","https://openalex.org/W4393857491","https://openalex.org/W4400073630","https://openalex.org/W4402187216","https://openalex.org/W4402716212","https://openalex.org/W4402915908","https://openalex.org/W4402955573","https://openalex.org/W4404931198"],"related_works":[],"abstract_inverted_index":{"In":[0],"autonomous":[1,59,190],"driving":[2,60,141,191],"and":[3,8,113,124,134,156,170,186],"robotics,":[4],"ensuring":[5],"road":[6],"safety":[7,185],"reliable":[9],"decision-making":[10],"critically":[11],"depends":[12],"on":[13,27,146],"out-of-distribution":[14],"(OOD)":[15],"segmentation.":[16],"While":[17],"numerous":[18],"methods":[19],"have":[20],"been":[21],"proposed":[22],"to":[23,76,131,182],"detect":[24],"anomalous":[25],"objects":[26,83,133],"the":[28,31,53,85,176,184],"road,":[29],"leveraging":[30],"vision-language":[32,86,93],"space\u2013which":[33],"provides":[34,135],"rich":[35],"linguistic":[36,46],"knowledge\u2013remains":[37],"an":[38],"underexplored":[39],"field.":[40],"We":[41],"hypothesize":[42],"that":[43,69,161],"incorporating":[44],"these":[45],"cues":[47],"can":[48],"be":[49],"especially":[50],"beneficial":[51],"in":[52,57,84,139],"complex":[54],"contexts":[55],"found":[56],"real-world":[58],"scenarios.To":[61],"this":[62],"end,":[63],"we":[64],"present":[65],"a":[66,71,78,92,97],"novel":[67],"approach":[68,90,128,163],"trains":[70],"Text-Driven":[72],"OOD":[73,102,115,119,137,149,180],"Segmentation":[74],"model":[75],"learn":[77],"semantically":[79],"diverse":[80,140],"set":[81],"of":[82,178,188],"space.":[87],"Concretely,":[88],"our":[89,127,162],"combines":[91],"model\u2019s":[94],"encoder":[95],"with":[96],"transformer":[98],"decoder,":[99],"employs":[100],"Distance-Based":[101],"prompts":[103],"located":[104],"at":[105],"varying":[106],"semantic":[107],"distances":[108],"from":[109],"in-distribution":[110],"(ID)":[111],"classes,":[112],"utilizes":[114],"Semantic":[116],"Augmentation":[117],"for":[118],"representaitons.":[120],"By":[121],"aligning":[122],"visual":[123],"textual":[125],"information,":[126],"effectively":[129],"generalizes":[130],"unseen":[132],"robust":[136],"segmentation":[138,150,181],"environments.We":[142],"conduct":[143],"extensive":[144],"experiments":[145],"publicly":[147],"available":[148],"datasets":[151],"such":[152],"as":[153],"Fishyscapes,":[154],"Segment-Me-If-You-Can,":[155],"Road":[157],"Anomaly":[158],"datasets,":[159],"demonstrating":[160],"achieves":[164],"state-of-the-art":[165],"performance":[166],"across":[167],"both":[168],"pixel-level":[169],"object-level":[171],"evaluations.":[172],"This":[173],"result":[174],"underscores":[175],"potential":[177],"vision-language\u2013based":[179],"bolster":[183],"reliability":[187],"future":[189],"systems.":[192]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}