Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382023992> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4382023992 endingPage "14" @default.
- W4382023992 startingPage "1" @default.
- W4382023992 abstract "Smart is a development trend in manufacturing systems, and intelligent defect recognition is essential in smart manufacturing systems for both quality control and decision-making. But the recognition performance of the current methods still needs to be improved, as well as the interpretability. As a hotspot, Transformer (ViT) has outstanding performance and interpretability on image recognition, which has shown the potential for intelligent defect recognition. However, ViT requires large numbers of samples, while small-sample is common in real-world cases, which contain less information, and this will cause ViT overfitting and misclassifying. Thus, it impedes the application of ViT greatly. To address this problem, a multi-scale spatial feature fusion-based ViT is proposed for small-sample defect recognition. The proposed method simulates human vision to extract the multi-level features of defects, and three improved ViTs are built to fuse the features. The experimental results indicate that the proposed method achieves improved performance on small-sample defect recognition. Compared with the DL and defect recognition methods, the accuracies are improved by 1.5%~20.07% on wood defects, and achieve an accuracy of 100% on steel defects. Furthermore, the visualization results also show that the proposed method is explicable, and it is helpful for defect analysis." @default.
- W4382023992 created "2023-06-27" @default.
- W4382023992 creator A5017886286 @default.
- W4382023992 creator A5055207211 @default.
- W4382023992 creator A5072179563 @default.
- W4382023992 date "2023-06-26" @default.
- W4382023992 modified "2023-09-23" @default.
- W4382023992 title "A Multi-level spatial feature fusion-based transformer for intelligent defect recognition with small samples toward smart manufacturing system" @default.
- W4382023992 cites W1988299413 @default.
- W4382023992 cites W2092072518 @default.
- W4382023992 cites W2194775991 @default.
- W4382023992 cites W2521720065 @default.
- W4382023992 cites W2531409750 @default.
- W4382023992 cites W2565639579 @default.
- W4382023992 cites W2805484002 @default.
- W4382023992 cites W2904910227 @default.
- W4382023992 cites W2920311927 @default.
- W4382023992 cites W2942285390 @default.
- W4382023992 cites W2944303778 @default.
- W4382023992 cites W2945708832 @default.
- W4382023992 cites W2961786565 @default.
- W4382023992 cites W2966341653 @default.
- W4382023992 cites W2980611806 @default.
- W4382023992 cites W2998008435 @default.
- W4382023992 cites W3017665024 @default.
- W4382023992 cites W3031794591 @default.
- W4382023992 cites W3039095521 @default.
- W4382023992 cites W3043445295 @default.
- W4382023992 cites W3087751617 @default.
- W4382023992 cites W3093398859 @default.
- W4382023992 cites W3193024002 @default.
- W4382023992 cites W3194342669 @default.
- W4382023992 cites W3194839486 @default.
- W4382023992 cites W3208023024 @default.
- W4382023992 cites W3210425911 @default.
- W4382023992 cites W3213886009 @default.
- W4382023992 cites W4200231646 @default.
- W4382023992 cites W4210407621 @default.
- W4382023992 cites W4221061181 @default.
- W4382023992 cites W4310791447 @default.
- W4382023992 doi "https://doi.org/10.1080/0951192x.2023.2229270" @default.
- W4382023992 hasPublicationYear "2023" @default.
- W4382023992 type Work @default.
- W4382023992 citedByCount "0" @default.
- W4382023992 crossrefType "journal-article" @default.
- W4382023992 hasAuthorship W4382023992A5017886286 @default.
- W4382023992 hasAuthorship W4382023992A5055207211 @default.
- W4382023992 hasAuthorship W4382023992A5072179563 @default.
- W4382023992 hasConcept C119599485 @default.
- W4382023992 hasConcept C119857082 @default.
- W4382023992 hasConcept C124101348 @default.
- W4382023992 hasConcept C127413603 @default.
- W4382023992 hasConcept C153180895 @default.
- W4382023992 hasConcept C154945302 @default.
- W4382023992 hasConcept C165801399 @default.
- W4382023992 hasConcept C22019652 @default.
- W4382023992 hasConcept C2781067378 @default.
- W4382023992 hasConcept C36464697 @default.
- W4382023992 hasConcept C41008148 @default.
- W4382023992 hasConcept C50644808 @default.
- W4382023992 hasConcept C66322947 @default.
- W4382023992 hasConceptScore W4382023992C119599485 @default.
- W4382023992 hasConceptScore W4382023992C119857082 @default.
- W4382023992 hasConceptScore W4382023992C124101348 @default.
- W4382023992 hasConceptScore W4382023992C127413603 @default.
- W4382023992 hasConceptScore W4382023992C153180895 @default.
- W4382023992 hasConceptScore W4382023992C154945302 @default.
- W4382023992 hasConceptScore W4382023992C165801399 @default.
- W4382023992 hasConceptScore W4382023992C22019652 @default.
- W4382023992 hasConceptScore W4382023992C2781067378 @default.
- W4382023992 hasConceptScore W4382023992C36464697 @default.
- W4382023992 hasConceptScore W4382023992C41008148 @default.
- W4382023992 hasConceptScore W4382023992C50644808 @default.
- W4382023992 hasConceptScore W4382023992C66322947 @default.
- W4382023992 hasFunder F4320321001 @default.
- W4382023992 hasLocation W43820239921 @default.
- W4382023992 hasOpenAccess W4382023992 @default.
- W4382023992 hasPrimaryLocation W43820239921 @default.
- W4382023992 hasRelatedWork W2948863132 @default.
- W4382023992 hasRelatedWork W2989932438 @default.
- W4382023992 hasRelatedWork W3011996705 @default.
- W4382023992 hasRelatedWork W3099765033 @default.
- W4382023992 hasRelatedWork W3165136198 @default.
- W4382023992 hasRelatedWork W3169068822 @default.
- W4382023992 hasRelatedWork W3174463126 @default.
- W4382023992 hasRelatedWork W4206534706 @default.
- W4382023992 hasRelatedWork W4229079080 @default.
- W4382023992 hasRelatedWork W4288336439 @default.
- W4382023992 isParatext "false" @default.
- W4382023992 isRetracted "false" @default.
- W4382023992 workType "article" @default.