Matches in SemOpenAlex for { <https://semopenalex.org/work/W3134113626> ?p ?o ?g. }
- W3134113626 abstract "Neural network-based anomaly detection methods have shown to achieve high performance. However, they require a large amount of training data for each task. We propose a neural network-based meta-learning method for supervised anomaly detection. The proposed method improves the anomaly detection performance on unseen tasks, which contains a few labeled normal and anomalous instances, by meta-training with various datasets. With a meta-learning framework, quick adaptation to each task and its effective backpropagation are important since the model is trained by the adaptation for each epoch. Our model enables them by formulating adaptation as a generalized eigenvalue problem with one-class classification; its global optimum solution is obtained, and the solver is differentiable. We experimentally demonstrate that the proposed method achieves better performance than existing anomaly detection and few-shot learning methods on various datasets." @default.
- W3134113626 created "2021-03-15" @default.
- W3134113626 creator A5030880294 @default.
- W3134113626 creator A5034538103 @default.
- W3134113626 date "2021-02-28" @default.
- W3134113626 modified "2023-09-23" @default.
- W3134113626 title "Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detection" @default.
- W3134113626 cites W1622922661 @default.
- W3134113626 cites W1876967670 @default.
- W3134113626 cites W1887038067 @default.
- W3134113626 cites W1964274671 @default.
- W3134113626 cites W1966081744 @default.
- W3134113626 cites W1995443851 @default.
- W3134113626 cites W2007087405 @default.
- W3134113626 cites W2045064676 @default.
- W3134113626 cites W2055587736 @default.
- W3134113626 cites W2059586807 @default.
- W3134113626 cites W2085756364 @default.
- W3134113626 cites W2091319256 @default.
- W3134113626 cites W2095705004 @default.
- W3134113626 cites W2101234009 @default.
- W3134113626 cites W2103441516 @default.
- W3134113626 cites W2122646361 @default.
- W3134113626 cites W2123399796 @default.
- W3134113626 cites W2127883478 @default.
- W3134113626 cites W2127979711 @default.
- W3134113626 cites W2131479143 @default.
- W3134113626 cites W2132870739 @default.
- W3134113626 cites W2137130182 @default.
- W3134113626 cites W2144182447 @default.
- W3134113626 cites W2150398577 @default.
- W3134113626 cites W2154884142 @default.
- W3134113626 cites W2166089138 @default.
- W3134113626 cites W2187089797 @default.
- W3134113626 cites W2187483593 @default.
- W3134113626 cites W2282861635 @default.
- W3134113626 cites W2296719434 @default.
- W3134113626 cites W2298457129 @default.
- W3134113626 cites W2340896621 @default.
- W3134113626 cites W2412589713 @default.
- W3134113626 cites W2432717477 @default.
- W3134113626 cites W2472819217 @default.
- W3134113626 cites W2599354622 @default.
- W3134113626 cites W2601450892 @default.
- W3134113626 cites W2604763608 @default.
- W3134113626 cites W2621614835 @default.
- W3134113626 cites W2665124875 @default.
- W3134113626 cites W2740930567 @default.
- W3134113626 cites W2742093937 @default.
- W3134113626 cites W2753160622 @default.
- W3134113626 cites W2753798143 @default.
- W3134113626 cites W2766669584 @default.
- W3134113626 cites W2771300315 @default.
- W3134113626 cites W2785902771 @default.
- W3134113626 cites W2787947370 @default.
- W3134113626 cites W2787957674 @default.
- W3134113626 cites W2793157857 @default.
- W3134113626 cites W2799251726 @default.
- W3134113626 cites W2803697594 @default.
- W3134113626 cites W2899771611 @default.
- W3134113626 cites W2910068345 @default.
- W3134113626 cites W2911964244 @default.
- W3134113626 cites W2912869723 @default.
- W3134113626 cites W2945655544 @default.
- W3134113626 cites W2946757877 @default.
- W3134113626 cites W2947883632 @default.
- W3134113626 cites W2951244377 @default.
- W3134113626 cites W2962791923 @default.
- W3134113626 cites W2962908092 @default.
- W3134113626 cites W2963045681 @default.
- W3134113626 cites W2963061824 @default.
- W3134113626 cites W2963070905 @default.
- W3134113626 cites W2963221401 @default.
- W3134113626 cites W2963557251 @default.
- W3134113626 cites W2963775850 @default.
- W3134113626 cites W2964078140 @default.
- W3134113626 cites W2964112702 @default.
- W3134113626 cites W2964121744 @default.
- W3134113626 cites W2964121937 @default.
- W3134113626 cites W2964206659 @default.
- W3134113626 cites W2970122980 @default.
- W3134113626 cites W2970535483 @default.
- W3134113626 cites W2978409868 @default.
- W3134113626 cites W2981368934 @default.
- W3134113626 cites W2990379018 @default.
- W3134113626 cites W2995458562 @default.
- W3134113626 cites W2999767092 @default.
- W3134113626 cites W3002105122 @default.
- W3134113626 cites W3034710639 @default.
- W3134113626 doi "https://doi.org/10.48550/arxiv.2103.00684" @default.
- W3134113626 hasPublicationYear "2021" @default.
- W3134113626 type Work @default.
- W3134113626 sameAs 3134113626 @default.
- W3134113626 citedByCount "0" @default.
- W3134113626 crossrefType "posted-content" @default.
- W3134113626 hasAuthorship W3134113626A5030880294 @default.
- W3134113626 hasAuthorship W3134113626A5034538103 @default.
- W3134113626 hasBestOaLocation W31341136261 @default.
- W3134113626 hasConcept C119857082 @default.
- W3134113626 hasConcept C120665830 @default.