FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3165716503> ?p ?o ?g. }

• W3165716503 endingPage "2465" @default.
• W3165716503 startingPage "2454" @default.
• W3165716503 abstract "Weakly supervised anomaly detection aims at learning an anomaly detector from a limited amount of labeled data and abundant unlabeled data. Recent works build deep neural networks for anomaly detection by discriminatively mapping the normal samples and abnormal samples to different regions in the feature space or fitting different distributions. However, due to the limited number of annotated anomaly samples, directly training networks with the discriminative loss may not be sufficient. To overcome this issue, this article proposes a novel strategy to transform the input data into a more meaningful representation that could be used for anomaly detection. Specifically, we leverage an autoencoder to encode the input data and utilize three factors, hidden representation, reconstruction residual vector, and reconstruction error, as the new representation for the input data. This representation amounts to encode a test sample with its projection on the training data manifold, its direction to its projection, and its distance to its projection. In addition to this encoding, we also propose a novel network architecture to seamlessly incorporate those three factors. From our extensive experiments, the benefits of the proposed strategy are clearly demonstrated by its superior performance over the competitive methods. Code is available at: https://github.com/yj-zhou/Feature_Encoding_with_AutoEncoders_for_Weakly-supervised_Anomaly_Detection." @default.
• W3165716503 created "2021-06-07" @default.
• W3165716503 creator A5016434114 @default.
• W3165716503 creator A5037482637 @default.
• W3165716503 creator A5037592037 @default.
• W3165716503 creator A5070976480 @default.
• W3165716503 creator A5074043004 @default.
• W3165716503 creator A5079799969 @default.
• W3165716503 date "2022-06-01" @default.
• W3165716503 modified "2023-10-16" @default.
• W3165716503 title "Feature Encoding With Autoencoders for Weakly Supervised Anomaly Detection" @default.
• W3165716503 cites W2099940443 @default.
• W3165716503 cites W2282861635 @default.
• W3165716503 cites W2348624827 @default.
• W3165716503 cites W2606538621 @default.
• W3165716503 cites W2743138268 @default.
• W3165716503 cites W2752875642 @default.
• W3165716503 cites W2756359217 @default.
• W3165716503 cites W2766761849 @default.
• W3165716503 cites W2783190965 @default.
• W3165716503 cites W2793988933 @default.
• W3165716503 cites W2799033092 @default.
• W3165716503 cites W2800094109 @default.
• W3165716503 cites W2807955733 @default.
• W3165716503 cites W2808472075 @default.
• W3165716503 cites W2808771744 @default.
• W3165716503 cites W2809108362 @default.
• W3165716503 cites W2902758299 @default.
• W3165716503 cites W2911528396 @default.
• W3165716503 cites W2918465401 @default.
• W3165716503 cites W2949848919 @default.
• W3165716503 cites W2968172454 @default.
• W3165716503 cites W2976482555 @default.
• W3165716503 cites W2979117328 @default.
• W3165716503 cites W2987228832 @default.
• W3165716503 cites W3033688252 @default.
• W3165716503 cites W3035699237 @default.
• W3165716503 cites W3048714446 @default.
• W3165716503 cites W3098957257 @default.
• W3165716503 cites W3103168224 @default.
• W3165716503 cites W3135550350 @default.
• W3165716503 cites W4213009331 @default.
• W3165716503 doi "https://doi.org/10.1109/tnnls.2021.3086137" @default.
• W3165716503 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34170831" @default.
• W3165716503 hasPublicationYear "2022" @default.
• W3165716503 type Work @default.
• W3165716503 sameAs 3165716503 @default.
• W3165716503 citedByCount "17" @default.
• W3165716503 countsByYear W31657165032021 @default.
• W3165716503 countsByYear W31657165032022 @default.
• W3165716503 countsByYear W31657165032023 @default.
• W3165716503 crossrefType "journal-article" @default.
• W3165716503 hasAuthorship W3165716503A5016434114 @default.
• W3165716503 hasAuthorship W3165716503A5037482637 @default.
• W3165716503 hasAuthorship W3165716503A5037592037 @default.
• W3165716503 hasAuthorship W3165716503A5070976480 @default.
• W3165716503 hasAuthorship W3165716503A5074043004 @default.
• W3165716503 hasAuthorship W3165716503A5079799969 @default.
• W3165716503 hasBestOaLocation W31657165032 @default.
• W3165716503 hasConcept C101738243 @default.
• W3165716503 hasConcept C104317684 @default.
• W3165716503 hasConcept C11413529 @default.
• W3165716503 hasConcept C116409475 @default.
• W3165716503 hasConcept C121332964 @default.
• W3165716503 hasConcept C125411270 @default.
• W3165716503 hasConcept C12997251 @default.
• W3165716503 hasConcept C138885662 @default.
• W3165716503 hasConcept C153083717 @default.
• W3165716503 hasConcept C153180895 @default.
• W3165716503 hasConcept C154945302 @default.
• W3165716503 hasConcept C17744445 @default.
• W3165716503 hasConcept C185592680 @default.
• W3165716503 hasConcept C199539241 @default.
• W3165716503 hasConcept C26873012 @default.
• W3165716503 hasConcept C2776359362 @default.
• W3165716503 hasConcept C2776401178 @default.
• W3165716503 hasConcept C41008148 @default.
• W3165716503 hasConcept C41895202 @default.
• W3165716503 hasConcept C50644808 @default.
• W3165716503 hasConcept C55493867 @default.
• W3165716503 hasConcept C57493831 @default.
• W3165716503 hasConcept C59404180 @default.
• W3165716503 hasConcept C66746571 @default.
• W3165716503 hasConcept C739882 @default.
• W3165716503 hasConcept C83665646 @default.
• W3165716503 hasConcept C94625758 @default.
• W3165716503 hasConcept C97931131 @default.
• W3165716503 hasConceptScore W3165716503C101738243 @default.
• W3165716503 hasConceptScore W3165716503C104317684 @default.
• W3165716503 hasConceptScore W3165716503C11413529 @default.
• W3165716503 hasConceptScore W3165716503C116409475 @default.
• W3165716503 hasConceptScore W3165716503C121332964 @default.
• W3165716503 hasConceptScore W3165716503C125411270 @default.
• W3165716503 hasConceptScore W3165716503C12997251 @default.
• W3165716503 hasConceptScore W3165716503C138885662 @default.
• W3165716503 hasConceptScore W3165716503C153083717 @default.
• W3165716503 hasConceptScore W3165716503C153180895 @default.
• W3165716503 hasConceptScore W3165716503C154945302 @default.

• next