FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380852790> ?p ?o ?g. }

• W4380852790 endingPage "60500" @default.
• W4380852790 startingPage "60490" @default.
• W4380852790 abstract "The past decade has witnessed wide applications of deep neural networks in anomaly detection. However, the dearth of interpretability in neural networks often hinders their reliability, especially for industrial applications where practical users heavily rely on interpretable methods to provide explanations for their decision-making. In this paper, we propose a reconstruction-based approach to unsupervised detection of anomalies in industrial defect data. Our algorithm employs an interpretability score during both the training and test phases. Specifically, we train an autoencoder with a loss function that incorporates an interpretability-aware error term. After training, the autoencoder processes a specific feature from the difference between the test image and the average of training images and produces an attention map that is used for detecting the anomalies. Our method not only achieves competitive performance compared with non-interpretability-aware methods but also produces attention maps that facilitate a direct explanation of detection results, which can potentially be useful for industrial practitioners." @default.
• W4380852790 created "2023-06-16" @default.
• W4380852790 creator A5035154955 @default.
• W4380852790 creator A5050241184 @default.
• W4380852790 creator A5056169947 @default.
• W4380852790 date "2023-01-01" @default.
• W4380852790 modified "2023-10-02" @default.
• W4380852790 title "Interpretability-Aware Industrial Anomaly Detection Using Autoencoders" @default.
• W4380852790 cites W1876967670 @default.
• W4380852790 cites W1970782782 @default.
• W4380852790 cites W1977556410 @default.
• W4380852790 cites W2010487804 @default.
• W4380852790 cites W2030553727 @default.
• W4380852790 cites W2107528096 @default.
• W4380852790 cites W2112680570 @default.
• W4380852790 cites W2124267685 @default.
• W4380852790 cites W2127979711 @default.
• W4380852790 cites W2131389289 @default.
• W4380852790 cites W2133665775 @default.
• W4380852790 cites W2135046866 @default.
• W4380852790 cites W2137130182 @default.
• W4380852790 cites W2142412278 @default.
• W4380852790 cites W2158756016 @default.
• W4380852790 cites W2295107390 @default.
• W4380852790 cites W2340896621 @default.
• W4380852790 cites W2489313985 @default.
• W4380852790 cites W2613480438 @default.
• W4380852790 cites W2737087486 @default.
• W4380852790 cites W2751378044 @default.
• W4380852790 cites W2756489700 @default.
• W4380852790 cites W2765427245 @default.
• W4380852790 cites W2789876780 @default.
• W4380852790 cites W2803255133 @default.
• W4380852790 cites W2809211248 @default.
• W4380852790 cites W2902164950 @default.
• W4380852790 cites W2907868778 @default.
• W4380852790 cites W2916229809 @default.
• W4380852790 cites W2920946673 @default.
• W4380852790 cites W2948982773 @default.
• W4380852790 cites W2962858109 @default.
• W4380852790 cites W2963061824 @default.
• W4380852790 cites W2963811535 @default.
• W4380852790 cites W2983029853 @default.
• W4380852790 cites W3006654525 @default.
• W4380852790 cites W3027056261 @default.
• W4380852790 cites W3034175346 @default.
• W4380852790 cites W3034648032 @default.
• W4380852790 cites W3038286218 @default.
• W4380852790 cites W3044215473 @default.
• W4380852790 cites W3105682467 @default.
• W4380852790 cites W3109715690 @default.
• W4380852790 cites W3118600296 @default.
• W4380852790 cites W3129467617 @default.
• W4380852790 cites W3135550350 @default.
• W4380852790 cites W3151160911 @default.
• W4380852790 cites W3169651898 @default.
• W4380852790 cites W3174422331 @default.
• W4380852790 cites W3200313969 @default.
• W4380852790 cites W3209793239 @default.
• W4380852790 cites W3212904554 @default.
• W4380852790 cites W4221021081 @default.
• W4380852790 cites W4226195497 @default.
• W4380852790 cites W4285814122 @default.
• W4380852790 doi "https://doi.org/10.1109/access.2023.3286548" @default.
• W4380852790 hasPublicationYear "2023" @default.
• W4380852790 type Work @default.
• W4380852790 citedByCount "1" @default.
• W4380852790 countsByYear W43808527902023 @default.
• W4380852790 crossrefType "journal-article" @default.
• W4380852790 hasAuthorship W4380852790A5035154955 @default.
• W4380852790 hasAuthorship W4380852790A5050241184 @default.
• W4380852790 hasAuthorship W4380852790A5056169947 @default.
• W4380852790 hasBestOaLocation W43808527901 @default.
• W4380852790 hasConcept C101738243 @default.
• W4380852790 hasConcept C108583219 @default.
• W4380852790 hasConcept C119857082 @default.
• W4380852790 hasConcept C121332964 @default.
• W4380852790 hasConcept C124101348 @default.
• W4380852790 hasConcept C138885662 @default.
• W4380852790 hasConcept C153180895 @default.
• W4380852790 hasConcept C154945302 @default.
• W4380852790 hasConcept C163258240 @default.
• W4380852790 hasConcept C2776401178 @default.
• W4380852790 hasConcept C2781067378 @default.
• W4380852790 hasConcept C41008148 @default.
• W4380852790 hasConcept C41895202 @default.
• W4380852790 hasConcept C43214815 @default.
• W4380852790 hasConcept C50644808 @default.
• W4380852790 hasConcept C62520636 @default.
• W4380852790 hasConcept C739882 @default.
• W4380852790 hasConceptScore W4380852790C101738243 @default.
• W4380852790 hasConceptScore W4380852790C108583219 @default.
• W4380852790 hasConceptScore W4380852790C119857082 @default.
• W4380852790 hasConceptScore W4380852790C121332964 @default.
• W4380852790 hasConceptScore W4380852790C124101348 @default.
• W4380852790 hasConceptScore W4380852790C138885662 @default.
• W4380852790 hasConceptScore W4380852790C153180895 @default.
• W4380852790 hasConceptScore W4380852790C154945302 @default.

• next