Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366310742> ?p ?o ?g. }
- W4366310742 endingPage "169" @default.
- W4366310742 startingPage "159" @default.
- W4366310742 abstract "Surface defect detection plays an important role in manufacturing and has aroused widespread interests. However, it is challenging as defects are highly similar to non-defects. To address this issue, this paper proposes a Region of Interest Attention (RoIA) network based on deep learning for automatically identifying surface defects. It consists of three parts: multi-level feature preservation (MFP) module, region proposal attention (RPA) module, and skip dense connection detection (SDCD) ones, where MFP is designed to differentiate defect features and texture information by feature reserved block, RPA is developed to locate the position of the defects by capturing global and local context information, and SDCD is proposed to better predict defect categories by propagating the fine-grained details from low-level feature map to high-level one. Experimental results conducted on three public datasets (e.g., NEU-DET, DAGM and Magnetic-Tile) demonstrate that the proposed method can significantly improve the detection performance than state-of-the-art ones and achieve an average defect detection accuracy of 99.49%." @default.
- W4366310742 created "2023-04-20" @default.
- W4366310742 creator A5043262479 @default.
- W4366310742 creator A5056210810 @default.
- W4366310742 creator A5073223793 @default.
- W4366310742 creator A5080122070 @default.
- W4366310742 date "2023-05-01" @default.
- W4366310742 modified "2023-10-18" @default.
- W4366310742 title "RoIA: Region of Interest Attention Network for Surface Defect Detection" @default.
- W4366310742 cites W2005219590 @default.
- W4366310742 cites W2064985253 @default.
- W4366310742 cites W2092072518 @default.
- W4366310742 cites W2113101204 @default.
- W4366310742 cites W2130931342 @default.
- W4366310742 cites W2293989912 @default.
- W4366310742 cites W2618530766 @default.
- W4366310742 cites W2888407265 @default.
- W4366310742 cites W2913074553 @default.
- W4366310742 cites W2920311927 @default.
- W4366310742 cites W2941001797 @default.
- W4366310742 cites W2955058313 @default.
- W4366310742 cites W2963037989 @default.
- W4366310742 cites W2963446712 @default.
- W4366310742 cites W2963706010 @default.
- W4366310742 cites W2975784364 @default.
- W4366310742 cites W2978742590 @default.
- W4366310742 cites W2994615081 @default.
- W4366310742 cites W2997903941 @default.
- W4366310742 cites W3013984308 @default.
- W4366310742 cites W3015335398 @default.
- W4366310742 cites W3015821169 @default.
- W4366310742 cites W3032280581 @default.
- W4366310742 cites W3046457381 @default.
- W4366310742 cites W3104156061 @default.
- W4366310742 cites W3108566774 @default.
- W4366310742 cites W3125817276 @default.
- W4366310742 cites W3132936317 @default.
- W4366310742 cites W3135064036 @default.
- W4366310742 cites W3139250374 @default.
- W4366310742 cites W3155079234 @default.
- W4366310742 cites W3196972528 @default.
- W4366310742 cites W3201267235 @default.
- W4366310742 cites W4213338244 @default.
- W4366310742 cites W4285819809 @default.
- W4366310742 cites W4286377374 @default.
- W4366310742 cites W4313270795 @default.
- W4366310742 cites W639708223 @default.
- W4366310742 doi "https://doi.org/10.1109/tsm.2023.3265987" @default.
- W4366310742 hasPublicationYear "2023" @default.
- W4366310742 type Work @default.
- W4366310742 citedByCount "0" @default.
- W4366310742 crossrefType "journal-article" @default.
- W4366310742 hasAuthorship W4366310742A5043262479 @default.
- W4366310742 hasAuthorship W4366310742A5056210810 @default.
- W4366310742 hasAuthorship W4366310742A5073223793 @default.
- W4366310742 hasAuthorship W4366310742A5080122070 @default.
- W4366310742 hasConcept C10138342 @default.
- W4366310742 hasConcept C115961682 @default.
- W4366310742 hasConcept C127313418 @default.
- W4366310742 hasConcept C138885662 @default.
- W4366310742 hasConcept C151730666 @default.
- W4366310742 hasConcept C153180895 @default.
- W4366310742 hasConcept C154945302 @default.
- W4366310742 hasConcept C159985019 @default.
- W4366310742 hasConcept C162324750 @default.
- W4366310742 hasConcept C192562407 @default.
- W4366310742 hasConcept C198082294 @default.
- W4366310742 hasConcept C2524010 @default.
- W4366310742 hasConcept C2776401178 @default.
- W4366310742 hasConcept C2776799497 @default.
- W4366310742 hasConcept C2777210771 @default.
- W4366310742 hasConcept C2779343474 @default.
- W4366310742 hasConcept C2780728851 @default.
- W4366310742 hasConcept C2781195486 @default.
- W4366310742 hasConcept C33923547 @default.
- W4366310742 hasConcept C41008148 @default.
- W4366310742 hasConcept C41895202 @default.
- W4366310742 hasConcept C50644808 @default.
- W4366310742 hasConceptScore W4366310742C10138342 @default.
- W4366310742 hasConceptScore W4366310742C115961682 @default.
- W4366310742 hasConceptScore W4366310742C127313418 @default.
- W4366310742 hasConceptScore W4366310742C138885662 @default.
- W4366310742 hasConceptScore W4366310742C151730666 @default.
- W4366310742 hasConceptScore W4366310742C153180895 @default.
- W4366310742 hasConceptScore W4366310742C154945302 @default.
- W4366310742 hasConceptScore W4366310742C159985019 @default.
- W4366310742 hasConceptScore W4366310742C162324750 @default.
- W4366310742 hasConceptScore W4366310742C192562407 @default.
- W4366310742 hasConceptScore W4366310742C198082294 @default.
- W4366310742 hasConceptScore W4366310742C2524010 @default.
- W4366310742 hasConceptScore W4366310742C2776401178 @default.
- W4366310742 hasConceptScore W4366310742C2776799497 @default.
- W4366310742 hasConceptScore W4366310742C2777210771 @default.
- W4366310742 hasConceptScore W4366310742C2779343474 @default.
- W4366310742 hasConceptScore W4366310742C2780728851 @default.
- W4366310742 hasConceptScore W4366310742C2781195486 @default.
- W4366310742 hasConceptScore W4366310742C33923547 @default.
- W4366310742 hasConceptScore W4366310742C41008148 @default.