FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3215156797> ?p ?o ?g. }

• W3215156797 endingPage "1487" @default.
• W3215156797 startingPage "1468" @default.
• W3215156797 abstract "A dual attention deep learning network is developed to classify three types of steel defects, locate their positions, and depict their shapes on the steel surface in an automatic and accurate manner. The novel pixel-level detection algorithm called DAN-DeepLabv3+ integrates a dual attention module into the DeepLabv3+ framework in pursue of more precise segmentation results. For one thing, the dual parallel attention module helps to explicitly model rich contextual dependencies over local feature representations in the spatial and channel dimensions. For another, the popular DeepLabv3+ in an encoder-decoder architecture is useful in capturing multi-scale contextual information and sharp object boundaries. The DAN-DeepLabv3+ is applied to an available dataset containing 6666 images, where three types of steel defects are taken by high-frequency cameras and have been annotated manually. Experimental results show that, compared with other deep learning models, DAN-DeepLabv3+ based on the Xception backbone exhibits the best segmentation performance under the mean intersection over union (IoU) of 89.95% and the frequency-weighted IoU of 97.34%. Besides, the F1-score for the three kinds of defects can reach 86.90%, 99.20%, and 92.81%. From the comparative study, it has been found that the adoption of the dual attention module and DeepLabv3+ contributes to boosting the segmentation performance. The significance of the proposed hybrid model lies in the enhancement in accurately detecting single or multiple steel defects, which has proven to outperform other classical methods." @default.
• W3215156797 created "2021-12-06" @default.
• W3215156797 creator A5006527469 @default.
• W3215156797 creator A5067890765 @default.
• W3215156797 date "2021-11-19" @default.
• W3215156797 modified "2023-10-11" @default.
• W3215156797 title "Dual attention deep learning network for automatic steel surface defect segmentation" @default.
• W3215156797 cites W1745334888 @default.
• W3215156797 cites W1903029394 @default.
• W3215156797 cites W2005029343 @default.
• W3215156797 cites W2033318022 @default.
• W3215156797 cites W2037227137 @default.
• W3215156797 cites W2071905184 @default.
• W3215156797 cites W2081857838 @default.
• W3215156797 cites W2090813402 @default.
• W3215156797 cites W2128880484 @default.
• W3215156797 cites W2412782625 @default.
• W3215156797 cites W2480078828 @default.
• W3215156797 cites W2560023338 @default.
• W3215156797 cites W2736832651 @default.
• W3215156797 cites W2736973763 @default.
• W3215156797 cites W2752782242 @default.
• W3215156797 cites W2794284562 @default.
• W3215156797 cites W2801492038 @default.
• W3215156797 cites W2804860796 @default.
• W3215156797 cites W2889035772 @default.
• W3215156797 cites W2889494142 @default.
• W3215156797 cites W2895340641 @default.
• W3215156797 cites W2905163589 @default.
• W3215156797 cites W2908667960 @default.
• W3215156797 cites W2911469685 @default.
• W3215156797 cites W2921440296 @default.
• W3215156797 cites W2941356554 @default.
• W3215156797 cites W2955058313 @default.
• W3215156797 cites W2963108253 @default.
• W3215156797 cites W2963372888 @default.
• W3215156797 cites W2963466857 @default.
• W3215156797 cites W2964309882 @default.
• W3215156797 cites W2966126335 @default.
• W3215156797 cites W2967525496 @default.
• W3215156797 cites W2967601546 @default.
• W3215156797 cites W2969297841 @default.
• W3215156797 cites W2981340875 @default.
• W3215156797 cites W2981413347 @default.
• W3215156797 cites W2989663977 @default.
• W3215156797 cites W2998847595 @default.
• W3215156797 cites W3005632666 @default.
• W3215156797 cites W3009712583 @default.
• W3215156797 cites W3010665872 @default.
• W3215156797 cites W3034681889 @default.
• W3215156797 cites W3034885317 @default.
• W3215156797 cites W3040396712 @default.
• W3215156797 cites W3042870837 @default.
• W3215156797 cites W3165034359 @default.
• W3215156797 cites W3177454358 @default.
• W3215156797 cites W3211685757 @default.
• W3215156797 doi "https://doi.org/10.1111/mice.12792" @default.
• W3215156797 hasPublicationYear "2021" @default.
• W3215156797 type Work @default.
• W3215156797 sameAs 3215156797 @default.
• W3215156797 citedByCount "24" @default.
• W3215156797 countsByYear W32151567972022 @default.
• W3215156797 countsByYear W32151567972023 @default.
• W3215156797 crossrefType "journal-article" @default.
• W3215156797 hasAuthorship W3215156797A5006527469 @default.
• W3215156797 hasAuthorship W3215156797A5067890765 @default.
• W3215156797 hasConcept C108583219 @default.
• W3215156797 hasConcept C111919701 @default.
• W3215156797 hasConcept C118505674 @default.
• W3215156797 hasConcept C124952713 @default.
• W3215156797 hasConcept C127413603 @default.
• W3215156797 hasConcept C138885662 @default.
• W3215156797 hasConcept C142362112 @default.
• W3215156797 hasConcept C146978453 @default.
• W3215156797 hasConcept C153180895 @default.
• W3215156797 hasConcept C154945302 @default.
• W3215156797 hasConcept C160633673 @default.
• W3215156797 hasConcept C2776401178 @default.
• W3215156797 hasConcept C2780980858 @default.
• W3215156797 hasConcept C31972630 @default.
• W3215156797 hasConcept C41008148 @default.
• W3215156797 hasConcept C41895202 @default.
• W3215156797 hasConcept C46686674 @default.
• W3215156797 hasConcept C64543145 @default.
• W3215156797 hasConcept C89600930 @default.
• W3215156797 hasConceptScore W3215156797C108583219 @default.
• W3215156797 hasConceptScore W3215156797C111919701 @default.
• W3215156797 hasConceptScore W3215156797C118505674 @default.
• W3215156797 hasConceptScore W3215156797C124952713 @default.
• W3215156797 hasConceptScore W3215156797C127413603 @default.
• W3215156797 hasConceptScore W3215156797C138885662 @default.
• W3215156797 hasConceptScore W3215156797C142362112 @default.
• W3215156797 hasConceptScore W3215156797C146978453 @default.
• W3215156797 hasConceptScore W3215156797C153180895 @default.
• W3215156797 hasConceptScore W3215156797C154945302 @default.
• W3215156797 hasConceptScore W3215156797C160633673 @default.
• W3215156797 hasConceptScore W3215156797C2776401178 @default.
• W3215156797 hasConceptScore W3215156797C2780980858 @default.

• next