{"id":"https://openalex.org/W4379929172","doi":"https://doi.org/10.1109/tim.2023.3284050","title":"MFNet: A Novel Multilevel Feature Fusion Network With Multibranch Structure for Surface Defect Detection","display_name":"MFNet: A Novel Multilevel Feature Fusion Network With Multibranch Structure for Surface Defect Detection","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4379929172","doi":"https://doi.org/10.1109/tim.2023.3284050"},"language":"en","primary_location":{"id":"doi:10.1109/tim.2023.3284050","doi":"https://doi.org/10.1109/tim.2023.3284050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tim.2023.3284050","pdf_url":null,"source":{"id":"https://openalex.org/S10892749","display_name":"IEEE Transactions on Instrumentation and Measurement","issn_l":"0018-9456","issn":["0018-9456","1557-9662"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","jufo-3","norway-1","poland-100","russia-white-list-1","vabb-shw"],"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 Instrumentation and Measurement","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.techrxiv.org/articles/preprint/MFNet_A_Novel_Multi-level_Feature_Fusion_Network_with_Multi-branch_Structure_for_Surface_Defect_Detection/21880884/1/files/38817120.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038618652","display_name":"Jiangping Zhu","orcid":"https://orcid.org/0000-0002-9756-5264","observed_orcids":["https://orcid.org/0000-0002-9756-5264"]},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangping Zhu","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-9756-5264","affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083725933","display_name":"Guohuan He","orcid":"https://orcid.org/0000-0001-9152-7294","observed_orcids":["https://orcid.org/0000-0001-9152-7294"]},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohuan He","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-9152-7294","affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070613964","display_name":"Pei Zhou","orcid":"https://orcid.org/0000-0003-1631-3637","observed_orcids":["https://orcid.org/0000-0003-1631-3637"]},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pei Zhou","raw_affiliation_strings":["College of Computer Science, Sichuan University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-1631-3637","affiliations":[{"raw_affiliation_string":"College of Computer Science, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24185976"],"apc_list":{"value":2345,"currency":"USD","value_usd":2345},"apc_paid":null,"fwci":1.9156,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85156913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"72","issue":null,"first_page":"1","last_page":"11"},"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":0.9994999766349792,"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":0.9994999766349792,"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/T11606","display_name":"Infrastructure Maintenance and Monitoring","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural 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/T12169","display_name":"Non-Destructive Testing Techniques","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/surface-defect-detection","display_name":"surface defect detection","score":1.0},{"id":"https://openalex.org/keywords/multilevel-feature-fusion","display_name":"multi-level feature fusion","score":0.9610000252723694},{"id":"https://openalex.org/keywords/atrous-spatial-pyramid-pooling","display_name":"atrous spatial pyramid pooling","score":0.9679999947547913},{"id":"https://openalex.org/keywords/global-attention-module","display_name":"global attention module","score":0.9369999766349792},{"id":"https://openalex.org/keywords/low-contrast-defect-detection","display_name":"low-contrast defect detection","score":0.6389999985694885},{"id":"https://openalex.org/keywords/small-object-detection","display_name":"small object detection","score":0.8230000138282776},{"id":"https://openalex.org/keywords/industrial-inspection","display_name":"industrial inspection","score":0.6110000014305115},{"id":"https://openalex.org/keywords/semantic-segmentation","display_name":"semantic segmentation","score":0.6779999732971191}],"concepts":[{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5758931636810303},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5306569337844849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5215349197387695},{"id":"https://openalex.org/C2776799497","wikidata":"https://www.wikidata.org/wiki/Q484298","display_name":"Surface (topology)","level":2,"score":0.4731494188308716},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3320958614349365},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17773139476776123},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10414209961891174},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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":4,"locations":[{"id":"doi:10.1109/tim.2023.3284050","doi":"https://doi.org/10.1109/tim.2023.3284050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tim.2023.3284050","pdf_url":null,"source":{"id":"https://openalex.org/S10892749","display_name":"IEEE Transactions on Instrumentation and Measurement","issn_l":"0018-9456","issn":["0018-9456","1557-9662"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","jufo-3","norway-1","poland-100","russia-white-list-1","vabb-shw"],"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 Instrumentation and Measurement","raw_type":"journal-article"},{"id":"doi:10.36227/techrxiv.21880884","doi":"https://doi.org/10.36227/techrxiv.21880884","is_oa":true,"landing_page_url":"https://doi.org/10.36227/techrxiv.21880884","pdf_url":"https://www.techrxiv.org/articles/preprint/MFNet_A_Novel_Multi-level_Feature_Fusion_Network_with_Multi-branch_Structure_for_Surface_Defect_Detection/21880884/1/files/38817120.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"TechRxiv","raw_type":"posted-content"},{"id":"doi:10.36227/techrxiv.21880884.v1","doi":"https://doi.org/10.36227/techrxiv.21880884.v1","is_oa":true,"landing_page_url":"http://dx.doi.org/10.36227/techrxiv.21880884.v1","pdf_url":"https://www.techrxiv.org/doi/pdf/10.36227/techrxiv.21880884.v1","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"pmh:oai:figshare.com:article/21880884","doi":null,"is_oa":true,"landing_page_url":"https://figshare.com/articles/preprint/MFNet_A_Novel_Multi-level_Feature_Fusion_Network_with_Multi-branch_Structure_for_Surface_Defect_Detection/21880884","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.36227/techrxiv.21880884","doi":"https://doi.org/10.36227/techrxiv.21880884","is_oa":true,"landing_page_url":"https://doi.org/10.36227/techrxiv.21880884","pdf_url":"https://www.techrxiv.org/articles/preprint/MFNet_A_Novel_Multi-level_Feature_Fusion_Network_with_Multi-branch_Structure_for_Surface_Defect_Detection/21880884/1/files/38817120.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"TechRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3524198529","display_name":null,"funder_award_id":"2021M692260","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G7598577333","display_name":null,"funder_award_id":"62101364","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7770988121","display_name":null,"funder_award_id":"2022YFG0053","funder_id":"https://openalex.org/F4320336596","funder_display_name":"Key Research and Development Program of Sichuan Province"},{"id":"https://openalex.org/G7819904838","display_name":null,"funder_award_id":"2021YFG0195","funder_id":"https://openalex.org/F4320336596","funder_display_name":"Key Research and Development Program of Sichuan Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320336596","display_name":"Key Research and Development Program of Sichuan Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4379929172.pdf","grobid_xml":"https://content.openalex.org/works/W4379929172.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2395611524","https://openalex.org/W2407692387","https://openalex.org/W2592939477","https://openalex.org/W2630837129","https://openalex.org/W2761216034","https://openalex.org/W2768489488","https://openalex.org/W2798122215","https://openalex.org/W2889985731","https://openalex.org/W2895420332","https://openalex.org/W2923486253","https://openalex.org/W2928165649","https://openalex.org/W2944303778","https://openalex.org/W2964309882","https://openalex.org/W2969860008","https://openalex.org/W2980098587","https://openalex.org/W2991627687","https://openalex.org/W2996290406","https://openalex.org/W3009886659","https://openalex.org/W3023248403","https://openalex.org/W3034552520","https://openalex.org/W3043497578","https://openalex.org/W3076555862","https://openalex.org/W3092482776","https://openalex.org/W3106583357","https://openalex.org/W3132963652","https://openalex.org/W3146188393","https://openalex.org/W3186285864","https://openalex.org/W3195969653","https://openalex.org/W3203305603","https://openalex.org/W4308602927","https://openalex.org/W4319073328","https://openalex.org/W4394643672","https://openalex.org/W6902547498"],"related_works":["https://openalex.org/W3106583357","https://openalex.org/W4289524245","https://openalex.org/W4382796361","https://openalex.org/W7131351900","https://openalex.org/W4392449567","https://openalex.org/W4206328147","https://openalex.org/W4292347971","https://openalex.org/W4376631578","https://openalex.org/W4387449002","https://openalex.org/W4410362149"],"abstract_inverted_index":{"Surface":[0],"defect":[1,64,147,169],"detection":[2,125],"is":[3,24,87,115],"an":[4,80],"essential":[5],"topic":[6],"in":[7,167],"the":[8,31,59,74,91,98,119,128],"industrial":[9,168],"inspection":[10],"field.":[11],"Many":[12],"methods":[13],"based":[14,76],"on":[15,77,144],"machine":[16],"vision":[17],"(MV)":[18],"have":[19],"been":[20],"applied.":[21],"However,":[22],"it":[23],"still":[25],"a":[26,51,101,111,162],"challenging":[27],"task":[28],"due":[29],"to":[30,89,104,117],"complexity":[32],"of":[33,94,121],"defects,":[34],"including":[35],"low-contrast,":[36],"small":[37],"objects,":[38],"and":[39,70,110,124,151],"irregular":[40],"geometric":[41],"boundaries.":[42],"To":[43],"deal":[44],"with":[45,58],"these":[46],"problems,":[47],"this":[48],"paper":[49],"proposes":[50],"novel":[52],"multi-level":[53,106],"feature":[54,122],"fusion":[55,123],"network":[56],"(MFNet)":[57],"multi-branch":[60,102],"structure":[61,103],"for":[62,108],"surface":[63],"detection.":[65],"Firstly,":[66],"we":[67],"extract":[68],"low-":[69],"high-level":[71],"features":[72,107],"via":[73],"encoder":[75],"ResNet34.":[78],"Secondly,":[79],"improved":[81],"atrous":[82],"spatial":[83],"pyramid":[84],"pooling":[85],"module":[86,114],"adapted":[88],"expand":[90],"receptive":[92],"field":[93],"low-level":[95],"features.":[96],"Then,":[97],"decoder":[99],"adopts":[100],"fuse":[105],"details,":[109],"global":[112],"attention":[113],"introduced":[116],"strengthen":[118],"effectiveness":[120],"accuracy.":[126],"Finally,":[127],"optimal":[129],"result":[130],"from":[131],"multiple":[132],"outputs":[133],"can":[134],"be":[135],"obtained":[136],"by":[137],"multi-branch.":[138],"Extensive":[139],"experiments":[140,156],"are":[141],"carried":[142],"out":[143],"three":[145],"representative":[146],"datasets:":[148],"CrackForest,":[149],"Kolektor,":[150],"RSDDs.":[152],"The":[153],"quantitatively":[154],"contrastive":[155],"prove":[157],"that":[158],"our":[159],"method":[160],"enjoys":[161],"better":[163],"semantic":[164,174],"segmentation":[165,175],"performance":[166],"detection,":[170],"outperforming":[171],"four":[172],"excellent":[173],"networks":[176],"(CrackForest:":[177],"Accuracy-98.54%,":[178],"F1-Score-74.71%,":[179],"IoU-60.22%;":[180],"Kolektor:":[181],"Accuracy-99.82%,":[182],"F1-Score-83.09%,":[183],"IoU-71.38%;":[184],"Type-\u2160":[185],"RSDDs:":[186],"Accuracy-99.79\\%,":[187],"F1-Score-85.09%,":[188],"IoU-74.84%).":[189]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-06-09T00:00:00"}