Matches in SemOpenAlex for { <https://semopenalex.org/work/W3117043194> ?p ?o ?g. }
- W3117043194 endingPage "107541" @default.
- W3117043194 startingPage "107541" @default.
- W3117043194 abstract "Abstract Automatic inspection methods based on machine vision have been widely employed for steel surface defect detection. The central purpose of these methods is to extract features to represent different defects. However, current methods depend on machine learning that demands handcrafted features and overlooks the domain shift. In this paper, we propose a new method combining domain adaptation (DA) and adaptive convolutional neural network (ACNN), called DA-ACNN, to achieve steel surface defect detection. The convolutional neural network (CNN) is used as the backbone. To account for the lack of labels in a new domain, we introduce an additional domain classifier and a constraint on label probability distribution to achieve the cross-domain and cross-task recognition. The normal distribution and the quadratic function are used to optimize the loss to improve the network performance. Adaptive learning rates based on the loss and the weight, respectively, are proposed to minimize the losses of DA and classification. We conducted experiments on steel surface defect datasets to validate the effectiveness of DA-ACNN. Compared with the classical CNN and other approaches, the results demonstrate the superiority of the proposed method." @default.
- W3117043194 created "2021-01-05" @default.
- W3117043194 creator A5013287421 @default.
- W3117043194 creator A5016991019 @default.
- W3117043194 creator A5017100408 @default.
- W3117043194 creator A5018881082 @default.
- W3117043194 creator A5056768519 @default.
- W3117043194 creator A5062117879 @default.
- W3117043194 date "2021-05-01" @default.
- W3117043194 modified "2023-10-18" @default.
- W3117043194 title "Visual inspection of steel surface defects based on domain adaptation and adaptive convolutional neural network" @default.
- W3117043194 cites W1884395441 @default.
- W3117043194 cites W2078087367 @default.
- W3117043194 cites W2196029350 @default.
- W3117043194 cites W2587088898 @default.
- W3117043194 cites W2591544917 @default.
- W3117043194 cites W2744604411 @default.
- W3117043194 cites W2786808285 @default.
- W3117043194 cites W2794659401 @default.
- W3117043194 cites W2802415864 @default.
- W3117043194 cites W2901051598 @default.
- W3117043194 cites W2901227701 @default.
- W3117043194 cites W2901639182 @default.
- W3117043194 cites W2904218127 @default.
- W3117043194 cites W2905416267 @default.
- W3117043194 cites W2907541186 @default.
- W3117043194 cites W2911810010 @default.
- W3117043194 cites W2911967554 @default.
- W3117043194 cites W2912073957 @default.
- W3117043194 cites W2924161931 @default.
- W3117043194 cites W2945708832 @default.
- W3117043194 cites W2953868242 @default.
- W3117043194 cites W2978231098 @default.
- W3117043194 cites W2982103539 @default.
- W3117043194 cites W2988659191 @default.
- W3117043194 cites W2990186851 @default.
- W3117043194 cites W2997838925 @default.
- W3117043194 cites W2998506103 @default.
- W3117043194 cites W3001472289 @default.
- W3117043194 cites W3002199135 @default.
- W3117043194 cites W3004668790 @default.
- W3117043194 cites W3005650655 @default.
- W3117043194 cites W3007092626 @default.
- W3117043194 cites W3024045805 @default.
- W3117043194 cites W3045896959 @default.
- W3117043194 cites W3048881327 @default.
- W3117043194 doi "https://doi.org/10.1016/j.ymssp.2020.107541" @default.
- W3117043194 hasPublicationYear "2021" @default.
- W3117043194 type Work @default.
- W3117043194 sameAs 3117043194 @default.
- W3117043194 citedByCount "33" @default.
- W3117043194 countsByYear W31170431942021 @default.
- W3117043194 countsByYear W31170431942022 @default.
- W3117043194 countsByYear W31170431942023 @default.
- W3117043194 crossrefType "journal-article" @default.
- W3117043194 hasAuthorship W3117043194A5013287421 @default.
- W3117043194 hasAuthorship W3117043194A5016991019 @default.
- W3117043194 hasAuthorship W3117043194A5017100408 @default.
- W3117043194 hasAuthorship W3117043194A5018881082 @default.
- W3117043194 hasAuthorship W3117043194A5056768519 @default.
- W3117043194 hasAuthorship W3117043194A5062117879 @default.
- W3117043194 hasConcept C134306372 @default.
- W3117043194 hasConcept C139807058 @default.
- W3117043194 hasConcept C153180895 @default.
- W3117043194 hasConcept C154945302 @default.
- W3117043194 hasConcept C15744967 @default.
- W3117043194 hasConcept C168820333 @default.
- W3117043194 hasConcept C169760540 @default.
- W3117043194 hasConcept C2524010 @default.
- W3117043194 hasConcept C2776434776 @default.
- W3117043194 hasConcept C2776799497 @default.
- W3117043194 hasConcept C28490314 @default.
- W3117043194 hasConcept C33923547 @default.
- W3117043194 hasConcept C36503486 @default.
- W3117043194 hasConcept C41008148 @default.
- W3117043194 hasConcept C50644808 @default.
- W3117043194 hasConcept C81363708 @default.
- W3117043194 hasConcept C95623464 @default.
- W3117043194 hasConceptScore W3117043194C134306372 @default.
- W3117043194 hasConceptScore W3117043194C139807058 @default.
- W3117043194 hasConceptScore W3117043194C153180895 @default.
- W3117043194 hasConceptScore W3117043194C154945302 @default.
- W3117043194 hasConceptScore W3117043194C15744967 @default.
- W3117043194 hasConceptScore W3117043194C168820333 @default.
- W3117043194 hasConceptScore W3117043194C169760540 @default.
- W3117043194 hasConceptScore W3117043194C2524010 @default.
- W3117043194 hasConceptScore W3117043194C2776434776 @default.
- W3117043194 hasConceptScore W3117043194C2776799497 @default.
- W3117043194 hasConceptScore W3117043194C28490314 @default.
- W3117043194 hasConceptScore W3117043194C33923547 @default.
- W3117043194 hasConceptScore W3117043194C36503486 @default.
- W3117043194 hasConceptScore W3117043194C41008148 @default.
- W3117043194 hasConceptScore W3117043194C50644808 @default.
- W3117043194 hasConceptScore W3117043194C81363708 @default.
- W3117043194 hasConceptScore W3117043194C95623464 @default.
- W3117043194 hasFunder F4320321001 @default.
- W3117043194 hasFunder F4320327912 @default.
- W3117043194 hasFunder F4320335787 @default.