{"id":"https://openalex.org/W4361828893","doi":"https://doi.org/10.1145/3582177.3582190","title":"Semi-supervised Defect Segmentation with Uncertainty-aware Pseudo-labels from Multi-branch Network","display_name":"Semi-supervised Defect Segmentation with Uncertainty-aware Pseudo-labels from Multi-branch Network","publication_year":2023,"publication_date":"2023-01-13","ids":{"openalex":"https://openalex.org/W4361828893","doi":"https://doi.org/10.1145/3582177.3582190"},"language":"en","primary_location":{"id":"doi:10.1145/3582177.3582190","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3582177.3582190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 5th International Conference on Image Processing and Machine Vision","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/A5016633415","display_name":"Dejene M. Sime","orcid":"https://orcid.org/0000-0002-7265-5765"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dejene M. Sime","raw_affiliation_strings":["University of Electronic Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0002-7265-5765","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029722566","display_name":"Guotai Wang","orcid":"https://orcid.org/0000-0002-8632-158X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guotai Wang","raw_affiliation_strings":["University of Electronic Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0002-8632-158X","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076564556","display_name":"Zhi Zeng","orcid":"https://orcid.org/0000-0002-0390-8917"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Zeng","raw_affiliation_strings":["University of Electronic Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0002-0390-8917","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012361632","display_name":"Bei Peng","orcid":"https://orcid.org/0000-0003-2486-6776"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bei Peng","raw_affiliation_strings":["University of Electronic Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0003-2486-6776","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04173057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"78"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14117","display_name":"Integrated Circuits and Semiconductor Failure Analysis","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11159","display_name":"Manufacturing Process and Optimization","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7324692606925964},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6851643323898315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5713390111923218},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40677958726882935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7324692606925964},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6851643323898315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5713390111923218},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40677958726882935}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3582177.3582190","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3582177.3582190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 5th International Conference on Image Processing and Machine Vision","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":20,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2418691539","https://openalex.org/W2782812883","https://openalex.org/W2923486253","https://openalex.org/W2945708832","https://openalex.org/W2962804657","https://openalex.org/W2979907638","https://openalex.org/W2992308087","https://openalex.org/W2994615081","https://openalex.org/W3016889634","https://openalex.org/W3035680157","https://openalex.org/W3087751617","https://openalex.org/W3104156061","https://openalex.org/W3119635706","https://openalex.org/W3164104137","https://openalex.org/W3171581326","https://openalex.org/W3203488660","https://openalex.org/W4295747380","https://openalex.org/W4312248619","https://openalex.org/W4313162490"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Semi-supervised":[0],"learning":[1,11,34,47],"methods":[2,26,127],"have":[3],"recently":[4],"gained":[5],"considerable":[6],"attention":[7],"for":[8,73],"training":[9,103],"deep":[10],"networks":[12],"with":[13,68],"limited":[14],"labeled":[15,130],"samples":[16],"and":[17,24,89,122],"additional":[18],"large":[19],"label-free":[20],"samples.":[21],"Consistency":[22],"regularization":[23],"pseudo-labeling":[25],"are":[27],"among":[28],"the":[29,43,79,82,86,90,101,107,118,143],"most":[30],"widely":[31],"used":[32],"semi-supervised":[33,74,125],"methods.":[35],"However,":[36],"unreliable":[37],"pseudo":[38,58],"labels":[39,59],"will":[40],"largely":[41],"limit":[42],"model\u2019s":[44],"performance":[45,115],"when":[46],"from":[48,61],"unlabeled":[49],"images.":[50],"To":[51],"alleviate":[52],"this":[53],"problem,":[54],"we":[55],"propose":[56],"uncertainty-rectified":[57],"generated":[60],"dynamically":[62],"mixing":[63],"predictions":[64],"of":[65,92],"multiple":[66],"decoders":[67],"a":[69],"shared":[70],"encoder":[71],"network":[72],"defect":[75],"segmentation.":[76],"We":[77,133],"estimated":[78,97],"uncertainty":[80,98],"as":[81,104,106],"prediction":[83,88],"discrepancy":[84],"between":[85],"average":[87],"output":[91],"each":[93],"decoder":[94],"head.":[95],"The":[96,110],"then":[99],"guides":[100],"consistency":[102],"well":[105,147],"pseudo-label-based":[108],"supervision.":[109],"proposed":[111,144],"method":[112,145],"achieved":[113],"significant":[114],"improvement":[116],"over":[117],"fully":[119],"supervised":[120],"baseline":[121],"other":[123],"state-of-the-art":[124],"segmentation":[126],"on":[128],"similar":[129],"data":[131],"proportions.":[132],"also":[134],"performed":[135],"an":[136],"extensive":[137],"ablation":[138],"study":[139],"to":[140],"demonstrate":[141],"that":[142],"performs":[146],"under":[148],"various":[149],"setups.":[150]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}