FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204383212> ?p ?o ?g. }

• W3204383212 abstract "Surface defect detection plays an increasingly important role in manufacturing industry to guarantee the product quality. Many deep learning methods have been widely used in surface defect detection tasks, and have been proven to perform well in defects classification and location. However, deep learning-based detection methods often require plenty of data for training, which fail to apply to the real industrial scenarios since the distribution of defect categories is often imbalanced. In other words, common defect classes have many samples but rare defect classes have extremely few samples, and it is difficult for these methods to well detect rare defect classes. To solve the imbalanced distribution problem, in this paper we propose TL-SDD: a novel Transfer Learning-based method for Surface Defect Detection. First, we adopt a two-phase training scheme to transfer the knowledge from common defect classes to rare defect classes. Second, we propose a novel Metric-based Surface Defect Detection (M-SDD) model. We design three modules for this model: (1) feature extraction module: containing feature fusion which combines high-level semantic information with low-level structural information. (2) feature reweighting module: transforming examples to a reweighting vector that indicates the importance of features. (3) distance metric module: learning a metric space in which defects are classified by computing distances to representations of each category. Finally, we validate the performance of our proposed method on a real dataset including surface defects of aluminum profiles. Compared to the baseline methods, the performance of our proposed method has improved by up to 11.98% for rare defect classes." @default.
• W3204383212 created "2021-10-11" @default.
• W3204383212 creator A5041610838 @default.
• W3204383212 creator A5047483277 @default.
• W3204383212 creator A5049531727 @default.
• W3204383212 creator A5056512791 @default.
• W3204383212 creator A5060451526 @default.
• W3204383212 creator A5075054211 @default.
• W3204383212 creator A5083721861 @default.
• W3204383212 date "2021-08-01" @default.
• W3204383212 modified "2023-10-16" @default.
• W3204383212 title "TL-SDD: A Transfer Learning-Based Method for Surface Defect Detection with Few Samples" @default.
• W3204383212 cites W1536680647 @default.
• W3204383212 cites W2067439776 @default.
• W3204383212 cites W2089575713 @default.
• W3204383212 cites W2131081720 @default.
• W3204383212 cites W2133059825 @default.
• W3204383212 cites W2166982406 @default.
• W3204383212 cites W2194775991 @default.
• W3204383212 cites W2295107390 @default.
• W3204383212 cites W2565639579 @default.
• W3204383212 cites W2598457882 @default.
• W3204383212 cites W2794550100 @default.
• W3204383212 cites W2888407265 @default.
• W3204383212 cites W2897772777 @default.
• W3204383212 cites W2912069721 @default.
• W3204383212 cites W2953868242 @default.
• W3204383212 cites W2955715150 @default.
• W3204383212 cites W2962793481 @default.
• W3204383212 cites W2962858109 @default.
• W3204383212 cites W2963679601 @default.
• W3204383212 cites W2965258271 @default.
• W3204383212 cites W2966341653 @default.
• W3204383212 cites W2974170420 @default.
• W3204383212 cites W2978183057 @default.
• W3204383212 cites W3011385666 @default.
• W3204383212 doi "https://doi.org/10.1109/bigcom53800.2021.00023" @default.
• W3204383212 hasPublicationYear "2021" @default.
• W3204383212 type Work @default.
• W3204383212 sameAs 3204383212 @default.
• W3204383212 citedByCount "4" @default.
• W3204383212 countsByYear W32043832122021 @default.
• W3204383212 countsByYear W32043832122022 @default.
• W3204383212 countsByYear W32043832122023 @default.
• W3204383212 crossrefType "proceedings-article" @default.
• W3204383212 hasAuthorship W3204383212A5041610838 @default.
• W3204383212 hasAuthorship W3204383212A5047483277 @default.
• W3204383212 hasAuthorship W3204383212A5049531727 @default.
• W3204383212 hasAuthorship W3204383212A5056512791 @default.
• W3204383212 hasAuthorship W3204383212A5060451526 @default.
• W3204383212 hasAuthorship W3204383212A5075054211 @default.
• W3204383212 hasAuthorship W3204383212A5083721861 @default.
• W3204383212 hasBestOaLocation W32043832122 @default.
• W3204383212 hasConcept C108583219 @default.
• W3204383212 hasConcept C119857082 @default.
• W3204383212 hasConcept C124101348 @default.
• W3204383212 hasConcept C127413603 @default.
• W3204383212 hasConcept C138885662 @default.
• W3204383212 hasConcept C150899416 @default.
• W3204383212 hasConcept C153180895 @default.
• W3204383212 hasConcept C154945302 @default.
• W3204383212 hasConcept C176217482 @default.
• W3204383212 hasConcept C21547014 @default.
• W3204383212 hasConcept C2524010 @default.
• W3204383212 hasConcept C2776401178 @default.
• W3204383212 hasConcept C2776799497 @default.
• W3204383212 hasConcept C33923547 @default.
• W3204383212 hasConcept C41008148 @default.
• W3204383212 hasConcept C41895202 @default.
• W3204383212 hasConcept C52622490 @default.
• W3204383212 hasConcept C83665646 @default.
• W3204383212 hasConceptScore W3204383212C108583219 @default.
• W3204383212 hasConceptScore W3204383212C119857082 @default.
• W3204383212 hasConceptScore W3204383212C124101348 @default.
• W3204383212 hasConceptScore W3204383212C127413603 @default.
• W3204383212 hasConceptScore W3204383212C138885662 @default.
• W3204383212 hasConceptScore W3204383212C150899416 @default.
• W3204383212 hasConceptScore W3204383212C153180895 @default.
• W3204383212 hasConceptScore W3204383212C154945302 @default.
• W3204383212 hasConceptScore W3204383212C176217482 @default.
• W3204383212 hasConceptScore W3204383212C21547014 @default.
• W3204383212 hasConceptScore W3204383212C2524010 @default.
• W3204383212 hasConceptScore W3204383212C2776401178 @default.
• W3204383212 hasConceptScore W3204383212C2776799497 @default.
• W3204383212 hasConceptScore W3204383212C33923547 @default.
• W3204383212 hasConceptScore W3204383212C41008148 @default.
• W3204383212 hasConceptScore W3204383212C41895202 @default.
• W3204383212 hasConceptScore W3204383212C52622490 @default.
• W3204383212 hasConceptScore W3204383212C83665646 @default.
• W3204383212 hasFunder F4320321001 @default.
• W3204383212 hasLocation W32043832121 @default.
• W3204383212 hasLocation W32043832122 @default.
• W3204383212 hasOpenAccess W3204383212 @default.
• W3204383212 hasPrimaryLocation W32043832121 @default.
• W3204383212 hasRelatedWork W2773120646 @default.
• W3204383212 hasRelatedWork W2946016983 @default.
• W3204383212 hasRelatedWork W2960456850 @default.
• W3204383212 hasRelatedWork W3031818154 @default.
• W3204383212 hasRelatedWork W3195938642 @default.
• W3204383212 hasRelatedWork W3197541072 @default.

• next