Matches in SemOpenAlex for { <https://semopenalex.org/work/W3129082918> ?p ?o ?g. }
- W3129082918 endingPage "57" @default.
- W3129082918 startingPage "46" @default.
- W3129082918 abstract "In industrial quality inspection, large amounts of data on the desired product appearance are available at the time of training, while significantly few defective samples are available. In this study, we proposed new memory-augmented adversarial autoencoders to detect and localize defects in real-time using defect-free samples alone for model training. This research was conducted by reconstructing images using an adversarial autoencoder and detection results from the Fréchet Markov distance (FMD). A threshold was determined based on the statistical characteristics of defect-free samples in the training set. Innovatively, we introduced a memory module and redesigned the reconstruction loss function to avoid the situation where the reconstruction ability is too strong or too poor, which lead to missing detection of defects. Then we proposed FMD, which can accurately measure the distance between the distribution of test samples and positive samples. Moreover, the statistics-based threshold determination method is used to meet different industrial needs. The accuracy, robustness, and computational overhead of the proposed MAA were evaluated using three datasets obtained from the production line and two benchmark datasets. The results indicated the effectiveness and ability of the proposed method to adapt to the real-time nature of industrial production." @default.
- W3129082918 created "2021-02-15" @default.
- W3129082918 creator A5029695887 @default.
- W3129082918 creator A5060454852 @default.
- W3129082918 creator A5068755803 @default.
- W3129082918 creator A5078691114 @default.
- W3129082918 creator A5083851866 @default.
- W3129082918 date "2022-02-01" @default.
- W3129082918 modified "2023-09-27" @default.
- W3129082918 title "Positive-Sample-Based Surface Defect Detection Using Memory-Augmented Adversarial Autoencoders" @default.
- W3129082918 cites W2025768430 @default.
- W3129082918 cites W2027937759 @default.
- W3129082918 cites W2078179989 @default.
- W3129082918 cites W2134490011 @default.
- W3129082918 cites W2183341477 @default.
- W3129082918 cites W2504252959 @default.
- W3129082918 cites W2599354622 @default.
- W3129082918 cites W2749684264 @default.
- W3129082918 cites W2756489700 @default.
- W3129082918 cites W2761216034 @default.
- W3129082918 cites W2889595641 @default.
- W3129082918 cites W2897689496 @default.
- W3129082918 cites W2912729634 @default.
- W3129082918 cites W2914570111 @default.
- W3129082918 cites W2948571212 @default.
- W3129082918 cites W2962793481 @default.
- W3129082918 cites W2963061824 @default.
- W3129082918 cites W2963156262 @default.
- W3129082918 cites W2987228832 @default.
- W3129082918 cites W3000384001 @default.
- W3129082918 cites W3027429685 @default.
- W3129082918 cites W3046248607 @default.
- W3129082918 cites W3086959365 @default.
- W3129082918 cites W3104156061 @default.
- W3129082918 doi "https://doi.org/10.1109/tmech.2021.3058147" @default.
- W3129082918 hasPublicationYear "2022" @default.
- W3129082918 type Work @default.
- W3129082918 sameAs 3129082918 @default.
- W3129082918 citedByCount "10" @default.
- W3129082918 countsByYear W31290829182022 @default.
- W3129082918 countsByYear W31290829182023 @default.
- W3129082918 crossrefType "journal-article" @default.
- W3129082918 hasAuthorship W3129082918A5029695887 @default.
- W3129082918 hasAuthorship W3129082918A5060454852 @default.
- W3129082918 hasAuthorship W3129082918A5068755803 @default.
- W3129082918 hasAuthorship W3129082918A5078691114 @default.
- W3129082918 hasAuthorship W3129082918A5083851866 @default.
- W3129082918 hasConcept C101738243 @default.
- W3129082918 hasConcept C104317684 @default.
- W3129082918 hasConcept C108583219 @default.
- W3129082918 hasConcept C119857082 @default.
- W3129082918 hasConcept C127413603 @default.
- W3129082918 hasConcept C13280743 @default.
- W3129082918 hasConcept C153180895 @default.
- W3129082918 hasConcept C154945302 @default.
- W3129082918 hasConcept C185592680 @default.
- W3129082918 hasConcept C185798385 @default.
- W3129082918 hasConcept C198531522 @default.
- W3129082918 hasConcept C205649164 @default.
- W3129082918 hasConcept C41008148 @default.
- W3129082918 hasConcept C43617362 @default.
- W3129082918 hasConcept C55493867 @default.
- W3129082918 hasConcept C63479239 @default.
- W3129082918 hasConcept C78519656 @default.
- W3129082918 hasConcept C99862985 @default.
- W3129082918 hasConceptScore W3129082918C101738243 @default.
- W3129082918 hasConceptScore W3129082918C104317684 @default.
- W3129082918 hasConceptScore W3129082918C108583219 @default.
- W3129082918 hasConceptScore W3129082918C119857082 @default.
- W3129082918 hasConceptScore W3129082918C127413603 @default.
- W3129082918 hasConceptScore W3129082918C13280743 @default.
- W3129082918 hasConceptScore W3129082918C153180895 @default.
- W3129082918 hasConceptScore W3129082918C154945302 @default.
- W3129082918 hasConceptScore W3129082918C185592680 @default.
- W3129082918 hasConceptScore W3129082918C185798385 @default.
- W3129082918 hasConceptScore W3129082918C198531522 @default.
- W3129082918 hasConceptScore W3129082918C205649164 @default.
- W3129082918 hasConceptScore W3129082918C41008148 @default.
- W3129082918 hasConceptScore W3129082918C43617362 @default.
- W3129082918 hasConceptScore W3129082918C55493867 @default.
- W3129082918 hasConceptScore W3129082918C63479239 @default.
- W3129082918 hasConceptScore W3129082918C78519656 @default.
- W3129082918 hasConceptScore W3129082918C99862985 @default.
- W3129082918 hasFunder F4320335787 @default.
- W3129082918 hasFunder F4320336026 @default.
- W3129082918 hasIssue "1" @default.
- W3129082918 hasLocation W31290829181 @default.
- W3129082918 hasOpenAccess W3129082918 @default.
- W3129082918 hasPrimaryLocation W31290829181 @default.
- W3129082918 hasRelatedWork W2567271240 @default.
- W3129082918 hasRelatedWork W2788487394 @default.
- W3129082918 hasRelatedWork W2922457425 @default.
- W3129082918 hasRelatedWork W3044458868 @default.
- W3129082918 hasRelatedWork W4213225422 @default.
- W3129082918 hasRelatedWork W4220775285 @default.
- W3129082918 hasRelatedWork W4250304930 @default.
- W3129082918 hasRelatedWork W4289656111 @default.
- W3129082918 hasRelatedWork W4289860834 @default.