Matches in SemOpenAlex for { <https://semopenalex.org/work/W4307995655> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4307995655 endingPage "004051752211352" @default.
- W4307995655 startingPage "004051752211352" @default.
- W4307995655 abstract "Deep-learning models have achieved state-of-the-art performances in a wide range of defect detection tasks. However, an inescapable criticism of one-stage fully supervised models is the lack of interpretability, which not only reduces the reliability of fabric defect detection systems but also limits the scope of their applications in production environments. To tackle the data imbalance and low interpretability of defect samples, we proposed a spatial cloze strategy for fabric defect detection, which reconstructs a local normal image and then feeds it into the detection model with the original image simultaneously. Specifically, we formulate the defect detection task as a novel image completion problem. Firstly, an end-to-end deep neural network is trained to finely restore the defect image by completing each image slice removed in sequence. Next, the progressive attention mechanism fuses the repaired normal image with the raw image, replacing the input layer of the cascade region-based convolutional neural network. Eventually, accurate instance-level defect segmentation can be obtained by comparing the repaired defect-free and the raw images. On the Tianchi dataset, the proposed method displays superior accuracy in 92% of defect classes, with a breakthrough in various categories that have hardly ever been detected. Extensive experiments on various complex fabric defect samples demonstrate that our strategy outperforms existing advanced methods." @default.
- W4307995655 created "2022-11-07" @default.
- W4307995655 creator A5029658365 @default.
- W4307995655 creator A5037423692 @default.
- W4307995655 creator A5046330935 @default.
- W4307995655 creator A5052722713 @default.
- W4307995655 date "2022-11-03" @default.
- W4307995655 modified "2023-09-28" @default.
- W4307995655 title "Fabric defect detection via a spatial cloze strategy" @default.
- W4307995655 cites W1536680647 @default.
- W4307995655 cites W1901129140 @default.
- W4307995655 cites W1975920834 @default.
- W4307995655 cites W1988646500 @default.
- W4307995655 cites W2022320998 @default.
- W4307995655 cites W2025285970 @default.
- W4307995655 cites W2031577896 @default.
- W4307995655 cites W2034856412 @default.
- W4307995655 cites W2034996255 @default.
- W4307995655 cites W2102605133 @default.
- W4307995655 cites W2133665775 @default.
- W4307995655 cites W2194775991 @default.
- W4307995655 cites W2899983521 @default.
- W4307995655 cites W2902770565 @default.
- W4307995655 cites W2946313203 @default.
- W4307995655 cites W2964241181 @default.
- W4307995655 cites W2994817145 @default.
- W4307995655 cites W3001472289 @default.
- W4307995655 cites W3009667969 @default.
- W4307995655 cites W3011537656 @default.
- W4307995655 cites W3031794591 @default.
- W4307995655 cites W3083951643 @default.
- W4307995655 cites W3093583063 @default.
- W4307995655 cites W3096831136 @default.
- W4307995655 cites W3103592385 @default.
- W4307995655 cites W3106250896 @default.
- W4307995655 cites W3116815602 @default.
- W4307995655 cites W3118440143 @default.
- W4307995655 cites W3198776009 @default.
- W4307995655 doi "https://doi.org/10.1177/00405175221135205" @default.
- W4307995655 hasPublicationYear "2022" @default.
- W4307995655 type Work @default.
- W4307995655 citedByCount "0" @default.
- W4307995655 crossrefType "journal-article" @default.
- W4307995655 hasAuthorship W4307995655A5029658365 @default.
- W4307995655 hasAuthorship W4307995655A5037423692 @default.
- W4307995655 hasAuthorship W4307995655A5046330935 @default.
- W4307995655 hasAuthorship W4307995655A5052722713 @default.
- W4307995655 hasConcept C108583219 @default.
- W4307995655 hasConcept C115961682 @default.
- W4307995655 hasConcept C138885662 @default.
- W4307995655 hasConcept C153180895 @default.
- W4307995655 hasConcept C154945302 @default.
- W4307995655 hasConcept C2776401178 @default.
- W4307995655 hasConcept C2781067378 @default.
- W4307995655 hasConcept C31972630 @default.
- W4307995655 hasConcept C41008148 @default.
- W4307995655 hasConcept C41895202 @default.
- W4307995655 hasConcept C50644808 @default.
- W4307995655 hasConcept C81363708 @default.
- W4307995655 hasConcept C89600930 @default.
- W4307995655 hasConceptScore W4307995655C108583219 @default.
- W4307995655 hasConceptScore W4307995655C115961682 @default.
- W4307995655 hasConceptScore W4307995655C138885662 @default.
- W4307995655 hasConceptScore W4307995655C153180895 @default.
- W4307995655 hasConceptScore W4307995655C154945302 @default.
- W4307995655 hasConceptScore W4307995655C2776401178 @default.
- W4307995655 hasConceptScore W4307995655C2781067378 @default.
- W4307995655 hasConceptScore W4307995655C31972630 @default.
- W4307995655 hasConceptScore W4307995655C41008148 @default.
- W4307995655 hasConceptScore W4307995655C41895202 @default.
- W4307995655 hasConceptScore W4307995655C50644808 @default.
- W4307995655 hasConceptScore W4307995655C81363708 @default.
- W4307995655 hasConceptScore W4307995655C89600930 @default.
- W4307995655 hasLocation W43079956551 @default.
- W4307995655 hasOpenAccess W4307995655 @default.
- W4307995655 hasPrimaryLocation W43079956551 @default.
- W4307995655 hasRelatedWork W2732542196 @default.
- W4307995655 hasRelatedWork W2738221750 @default.
- W4307995655 hasRelatedWork W2760085659 @default.
- W4307995655 hasRelatedWork W2971526870 @default.
- W4307995655 hasRelatedWork W2994948129 @default.
- W4307995655 hasRelatedWork W3102253946 @default.
- W4307995655 hasRelatedWork W3144574764 @default.
- W4307995655 hasRelatedWork W3156786002 @default.
- W4307995655 hasRelatedWork W4226289457 @default.
- W4307995655 hasRelatedWork W4293211451 @default.
- W4307995655 isParatext "false" @default.
- W4307995655 isRetracted "false" @default.
- W4307995655 workType "article" @default.