{"id":"https://openalex.org/W7137814749","doi":"https://doi.org/10.1609/aaai.v40i18.38572","title":"A Novel Fine-Tuned CLIP-OOD Detection Method with Double Loss Constraint Through Optimal Transport Semantic Alignment","display_name":"A Novel Fine-Tuned CLIP-OOD Detection Method with Double Loss Constraint Through Optimal Transport Semantic Alignment","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137814749","doi":"https://doi.org/10.1609/aaai.v40i18.38572"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i18.38572","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i18.38572","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i18.38572","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129673631","display_name":"Hengyang Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hengyang Lu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129666623","display_name":"Xin Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Guo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129710065","display_name":"Shuai Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Feng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102020790","display_name":"Wenyu Jiang","orcid":"https://orcid.org/0000-0002-4539-7596"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenyu Jiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129722692","display_name":"Yuntao Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuntao Du","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086901569","display_name":"Chang Sheng Xia","orcid":"https://orcid.org/0000-0001-6614-155X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang Xia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129690463","display_name":"Chenyou Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenyou Fan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5129673631"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02300696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"18","first_page":"15448","last_page":"15456"},"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":0.19470000267028809,"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":0.19470000267028809,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11209999769926071,"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":0.09989999979734421,"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/constraint","display_name":"Constraint (computer-aided design)","score":0.7784000039100647},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.7491999864578247},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6952999830245972},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6812000274658203},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.625},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6177999973297119},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.4530999958515167},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41749998927116394}],"concepts":[{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.7784000039100647},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.7491999864578247},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6952999830245972},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6812000274658203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6712999939918518},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.625},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6177999973297119},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43290001153945923},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4235999882221222},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41749998927116394},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.3497999906539917},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33219999074935913},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30059999227523804},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2897999882698059},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i18.38572","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i18.38572","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i18.38572","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i18.38572","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7869814038276672,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Detecting":[0],"Out-Of-Distribution":[1],"(OOD)":[2],"samples":[3],"in":[4,153],"image":[5,35,44,145],"classification":[6],"is":[7,140],"crucial":[8],"for":[9],"model":[10],"reliability.":[11],"With":[12],"the":[13,28,34,41,55,75,86,101,108,118,137,154,158,163,170],"rise":[14],"of":[15,37,43,121,157],"Vision-Language":[16],"Models":[17],"(VLMs),":[18],"CLIP-OOD":[19],"has":[20],"become":[21],"a":[22,68],"research":[23],"hotspot.":[24],"However,":[25],"we":[26,66],"observe":[27],"Low":[29],"Focus":[30],"Attention":[31],"phenomenon":[32,52],"from":[33,54,172],"encoders":[36,45],"CLIP,":[38],"which":[39,113],"means":[40],"attention":[42],"often":[46],"spreads":[47],"to":[48,142,174],"non-in-distribution":[49],"regions.":[50],"This":[51],"comes":[53],"semantic":[56,127],"mismalignment":[57],"and":[58,92,107,124,133,168],"inter-class":[59,131],"feature":[60,146],"confusion.":[61],"To":[62],"address":[63],"these":[64],"issues,":[65],"propose":[67],"novel":[69],"fine-tuned":[70],"OOD":[71],"detection":[72],"method":[73],"with":[74,177],"Double":[76,87],"loss":[77],"constraint":[78],"based":[79],"on":[80,117],"Optimal":[81,93],"Transport":[82,94],"(DOT-OOD).":[83],"DOT-OOD":[84,161],"integrates":[85],"Loss":[88,106],"Constraint":[89],"(DLC)":[90],"module":[91,99,139],"(OT)":[95],"module.":[96],"The":[97],"DLC":[98],"comprises":[100],"Aligned":[102],"Image-Text":[103],"Concept":[104],"Matching":[105],"Negative":[109],"Sample":[110],"Repulsion":[111],"Loss,":[112],"respectively":[114],"(1)":[115],"focus":[116],"core":[119],"semantics":[120],"ID":[122],"images":[123],"achieve":[125],"cross-modal":[126],"alignment,":[128],"(2)":[129],"expand":[130],"distances":[132],"enhance":[134],"discriminative.":[135],"While":[136],"OT":[138],"introduced":[141],"obtain":[143],"enhanced":[144],"representations.":[147],"Extensive":[148],"experimental":[149],"results":[150],"show":[151],"that":[152],"16-shot":[155],"scenario":[156],"ImageNet-1k":[159],"benchmark,":[160],"reduces":[162],"FPR95":[164],"by":[165],"over":[166],"10%":[167],"improves":[169],"AUROC":[171],"94.48%":[173],"96.57%":[175],"compared":[176],"SOTAs.":[178]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}