{"id":"https://openalex.org/W4408353797","doi":"https://doi.org/10.1109/icassp49660.2025.10889356","title":"InstAD: Instance-aware Segmentation Framework for Zero-shot Multi-instance Anomaly Detection","display_name":"InstAD: Instance-aware Segmentation Framework for Zero-shot Multi-instance Anomaly Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353797","doi":"https://doi.org/10.1109/icassp49660.2025.10889356"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5110924073","display_name":"Cheng\u2010Yu Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Cheng-Yu Ho","raw_affiliation_strings":["National Tsing-Hua University,Department of Computer Science,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing-Hua University,Department of Computer Science,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073849580","display_name":"Shang\u2010Hong Lai","orcid":"https://orcid.org/0000-0002-5092-993X"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shang-Hong Lai","raw_affiliation_strings":["National Tsing-Hua University,Department of Computer Science,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing-Hua University,Department of Computer Science,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110924073"],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02044233,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9581000208854675,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9387999773025513,"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/computer-science","display_name":"Computer science","score":0.690218448638916},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.628166675567627},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5730569362640381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5523404479026794},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5250748991966248},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43510112166404724},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4102877974510193}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.690218448638916},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.628166675567627},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5730569362640381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5523404479026794},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5250748991966248},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43510112166404724},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4102877974510193},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2948982773","https://openalex.org/W2964137095","https://openalex.org/W3147184966","https://openalex.org/W3169651898","https://openalex.org/W4200434100","https://openalex.org/W4212874935","https://openalex.org/W4312605624","https://openalex.org/W4319299987","https://openalex.org/W4386065385","https://openalex.org/W4390874575","https://openalex.org/W4393154102","https://openalex.org/W4393158476","https://openalex.org/W4394597890","https://openalex.org/W4394625793","https://openalex.org/W4402716375","https://openalex.org/W4402961681","https://openalex.org/W4403780904","https://openalex.org/W6791353385","https://openalex.org/W6846276983","https://openalex.org/W6858057904","https://openalex.org/W6861232000"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Multi-instance":[0],"anomaly":[1,38,83,143],"detection":[2,19,39,84,144],"and":[3,25,57,89,93,108,118,122,145],"segmentation":[4,49,64],"play":[5],"a":[6,35],"crucial":[7],"role":[8],"in":[9],"automated":[10],"industrial":[11],"inspection.":[12],"Previous":[13],"works":[14],"mainly":[15],"focus":[16],"on":[17,101,128],"single-instance":[18],"tasks":[20],"that":[21,41,132],"require":[22],"well-aligned":[23],"input":[24],"extensive":[26],"training":[27],"sets.":[28],"In":[29],"this":[30],"work,":[31],"we":[32,60,86,115],"introduce":[33],"InstAD,":[34],"zero-shot":[36,113],"multi-instance":[37,77,103,142],"framework":[40],"achieves":[42],"high":[43],"accuracy":[44],"with":[45,66,97],"unaligned":[46],"multi-instances.":[47],"Combining":[48],"results":[50,65],"from":[51],"the":[52,63,67,98,102,106,112,133],"Segment":[53],"Anything":[54],"Model":[55],"[1]":[56],"Grounded-SAM":[58],"[2],":[59],"further":[61],"refine":[62],"proposed":[68,134],"Adaptive":[69],"Bandwidth":[70],"Segmentation":[71],"Refinement":[72],"scheme":[73],"to":[74],"achieve":[75,87],"accurate":[76],"segmentation.":[78,146],"By":[79],"using":[80],"our":[81],"instance-aware":[82],"strategy,":[85],"93.0%":[88],"99.1%":[90],"for":[91,120,141],"image-level":[92,121],"pixel-level":[94,123],"AUROC,":[95,124],"respectively,":[96],"four-shot":[99],"setting":[100],"classes":[104],"of":[105],"VisA":[107],"MPDD":[109],"datasets.":[110],"Under":[111],"scenario,":[114],"reach":[116],"87.2%":[117],"98.4%":[119],"respectively.":[125],"Our":[126],"experiments":[127],"public":[129],"datasets":[130],"show":[131],"InstAD":[135],"method":[136],"significantly":[137],"outperforms":[138],"SOTA":[139],"methods":[140]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}