{"id":"https://openalex.org/W4415538059","doi":"https://doi.org/10.1145/3746027.3754465","title":"Omni-LLaMA-AD: A Unified Model for Open-Set Visual Anomaly Detection","display_name":"Omni-LLaMA-AD: A Unified Model for Open-Set Visual Anomaly Detection","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538059","doi":"https://doi.org/10.1145/3746027.3754465"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754465","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5089539994","display_name":"Rongyu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongyu Zhang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-9417-4053","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102815784","display_name":"Zhanbin Hu","orcid":"https://orcid.org/0009-0008-4719-8356"},"institutions":[{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanbin Hu","raw_affiliation_strings":["Beijing Information Science and Technology University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-4719-8356","affiliations":[{"raw_affiliation_string":"Beijing Information Science and Technology University, Beijing, China","institution_ids":["https://openalex.org/I78675632"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047964053","display_name":"Jiamu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiamu Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-1208-9585","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087942458","display_name":"Qiang Zhu","orcid":"https://orcid.org/0000-0002-2405-6776"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Zhu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2405-6776","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26952571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13492","last_page":"13494"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998999834060669,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998999834060669,"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/T11438","display_name":"Retinal Imaging and Analysis","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T14319","display_name":"Currency Recognition and Detection","score":0.9912999868392944,"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/unified-model","display_name":"Unified Model","score":0.8133000135421753},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.7760000228881836},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7211999893188477},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.6782000064849854},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5685999989509583},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35120001435279846}],"concepts":[{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.8133000135421753},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7760000228881836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7293999791145325},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7211999893188477},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.6782000064849854},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5685999989509583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5167999863624573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3319000005722046},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29510000348091125}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754465","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2948982773","https://openalex.org/W4212874935","https://openalex.org/W4386065385","https://openalex.org/W4393158476"],"related_works":[],"abstract_inverted_index":{"Visual":[0],"anomaly":[1,41,78,99],"detection":[2,79],"(VAD)":[3],"aims":[4],"to":[5,96],"identify":[6],"image":[7],"regions":[8],"that":[9],"deviate":[10],"from":[11],"established":[12],"normal":[13,84],"patterns.":[14],"Existing":[15],"methods":[16],"often":[17],"rely":[18],"on":[19,52],"domain-specific":[20,88],"training":[21],"and":[22,63,72,86,104,112],"follow":[23],"a":[24,53,60,82],"''one-class-one-model''":[25],"paradigm,":[26],"limiting":[27],"scalability.":[28],"We":[29],"propose":[30],"Omni-LLaMA-AD,":[31],"the":[32,57,93],"first":[33],"unified":[34],"multimodal":[35],"large":[36],"language":[37],"model":[38,58],"for":[39],"open-set":[40],"detection,":[42],"capable":[43],"of":[44],"handling":[45],"diverse":[46],"domains":[47],"with":[48,80],"minimal":[49],"supervision.":[50],"Built":[51],"pretrained":[54],"LLaMA":[55],"backbone,":[56],"uses":[59],"VQGAN-based":[61],"tokenizer":[62],"supports":[64],"joint":[65],"vision-language":[66,70],"generation.":[67],"Trained":[68],"via":[69],"alignment":[71],"instruction":[73],"tuning,":[74],"it":[75],"achieves":[76],"effective":[77],"only":[81],"few":[83],"samples":[85],"no":[87],"fine-tuning.":[89],"Our":[90],"demo":[91],"showcases":[92],"model's":[94],"ability":[95],"generate":[97],"high-quality":[98],"masks":[100],"across":[101],"industrial,":[102],"medical,":[103],"logical":[105],"datasets,":[106],"highlighting":[107],"its":[108],"strong":[109],"cross-domain":[110],"generalization":[111],"interactive":[113],"dialogue-based":[114],"user":[115],"experience.":[116]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}