{"id":"https://openalex.org/W4417536083","doi":"https://doi.org/10.1109/tip.2026.3697648","title":"IQE-CLIP: Instance-Aware Query Embedding for Zero-/Few-Shot Anomaly Detection in Medical Domain","display_name":"IQE-CLIP: Instance-Aware Query Embedding for Zero-/Few-Shot Anomaly Detection in Medical Domain","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417536083","doi":"https://doi.org/10.1109/tip.2026.3697648","pmid":"https://pubmed.ncbi.nlm.nih.gov/42228658"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3697648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3697648","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.10730","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5143242062","display_name":"Hong Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hong Huang","raw_affiliation_strings":["School of Computing Science, Simon Fraser University, Vancouver, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Science, Simon Fraser University, Vancouver, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126159596","display_name":"Weixiang Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weixiang Sun","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Notre Dame, South Bend, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame, South Bend, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042499646","display_name":"Zhijian Wu","orcid":"https://orcid.org/0000-0002-3040-3287"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijian Wu","raw_affiliation_strings":["Medical Artificial Intelligence Laboratory, Westlake University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3040-3287","affiliations":[{"raw_affiliation_string":"Medical Artificial Intelligence Laboratory, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014222179","display_name":"Donghuan Lu","orcid":"https://orcid.org/0000-0002-8399-7410"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donghuan Lu","raw_affiliation_strings":["Tencent Jarvis Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-8399-7410","affiliations":[{"raw_affiliation_string":"Tencent Jarvis Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352418","display_name":"Xian Wu","orcid":"https://orcid.org/0000-0003-1118-9710"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Wu","raw_affiliation_strings":["Tencent Jarvis Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1118-9710","affiliations":[{"raw_affiliation_string":"Tencent Jarvis Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051649145","display_name":"Yefeng Zheng","orcid":"https://orcid.org/0000-0003-2195-2847"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yefeng Zheng","raw_affiliation_strings":["Medical Artificial Intelligence Laboratory, Westlake University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2195-2847","affiliations":[{"raw_affiliation_string":"Medical Artificial Intelligence Laboratory, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"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":0.02140226,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"6153","last_page":"6166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.8220999836921692,"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":0.8220999836921692,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.07840000092983246,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.023600000888109207,"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/embedding","display_name":"Embedding","score":0.6500999927520752},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.5845999717712402},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.544700026512146},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.48190000653266907},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.475600004196167},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.40959998965263367},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.37599998712539673},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.36959999799728394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8043000102043152},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6500999927520752},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.5845999717712402},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5562000274658203},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.544700026512146},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48190000653266907},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.40959998965263367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4032000005245209},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3472000062465668},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33329999446868896},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.3109000027179718},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.30550000071525574},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.27549999952316284},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.2639999985694885},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C96956885","wikidata":"https://www.wikidata.org/wiki/Q6138701","display_name":"RDF query language","level":5,"score":0.2542000114917755}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tip.2026.3697648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3697648","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:42228658","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42228658","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null},{"id":"pmh:oai:arXiv.org:2506.10730","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.10730","pdf_url":"https://arxiv.org/pdf/2506.10730","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.10730","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.10730","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.10730","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.10730","pdf_url":"https://arxiv.org/pdf/2506.10730","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"Recently,":[0],"the":[1,54,67,100,141,165],"rapid":[2],"advancements":[3],"of":[4,31,60,138,167],"vision-language":[5],"models,":[6],"such":[7,44],"as":[8,104],"CLIP,":[9],"have":[10],"led":[11],"to":[12,40,140,152,174],"significant":[13],"progress":[14],"in":[15,53,78,99],"zero-/few-shot":[16],"anomaly":[17],"detection":[18],"(ZFSAD)":[19],"tasks.":[20,87,194],"However,":[21],"most":[22],"existing":[23],"CLIP-based":[24],"ZFSAD":[25,73,97],"methods":[26,74],"commonly":[27],"assume":[28],"prior":[29],"knowledge":[30],"categories":[32],"and":[33,63,115,131,161,192,198],"rely":[34],"on":[35,179,189],"carefully":[36],"crafted":[37],"prompts":[38,48,160],"tailored":[39],"specific":[41],"scenarios.":[42],"While":[43],"meticulously":[45],"designed":[46],"text":[47,159],"effectively":[49],"capture":[50],"semantic":[51],"information":[52,156],"textual":[55,114],"space,":[56],"they":[57],"fall":[58],"short":[59],"distinguishing":[61],"normal":[62],"anomalous":[64],"instances":[65],"within":[66],"joint":[68],"embedding":[69],"space.":[70],"Moreover,":[71],"these":[72],"are":[75,119,171,200],"predominantly":[76],"explored":[77],"industrial":[79],"scenarios,":[80],"with":[81],"few":[82],"efforts":[83],"conducted":[84,178],"for":[85,96,122,135],"medical":[86,101,142,181],"To":[88],"this":[89],"end,":[90],"we":[91,125,145],"propose":[92],"an":[93,147],"innovative":[94],"framework":[95],"tasks":[98],"domain,":[102],"denoted":[103],"IQE-CLIP.":[105],"We":[106],"reveal":[107],"that":[108,170,184],"query":[109,149,168],"embeddings,":[110],"which":[111],"incorporate":[112],"both":[113,158,190],"instance-aware":[116,148],"visual":[117,162],"information,":[118],"better":[120,136],"indicators":[121],"abnormalities.":[123],"Specifically,":[124],"first":[126],"introduce":[127],"class-based":[128],"prompting":[129,133],"tokens":[130,134],"learnable":[132],"adaptation":[137],"CLIP":[139],"domain.":[143],"Then,":[144],"design":[146],"module":[150],"(IQM)":[151],"extract":[153],"region-level":[154],"contextual":[155],"from":[157],"features,":[163],"enabling":[164],"generation":[166],"embeddings":[169],"more":[172],"sensitive":[173],"anomalies.":[175],"Extensive":[176],"experiments":[177],"six":[180],"datasets":[182],"demonstrate":[183],"IQE-CLIP":[185],"achieves":[186],"state-of-the-art":[187],"performance":[188],"zero-shot":[191],"few-shot":[193],"The":[195],"source":[196],"code":[197],"data":[199],"available":[201],"at":[202],"https://github.com/hongh0/IQE-CLIP.":[203]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}