FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2948079128> ?p ?o ?g. }

• W2948079128 abstract "Deep approaches to anomaly detection have recently shown promising results over shallow methods on large and complex datasets. Typically anomaly detection is treated as an unsupervised learning problem. In practice however, one may have---in addition to a large set of unlabeled samples---access to a small pool of labeled samples, e.g. a subset verified by some domain expert as being normal or anomalous. Semi-supervised approaches to anomaly detection aim to utilize such labeled samples, but most proposed methods are limited to merely including labeled normal samples. Only a few methods take advantage of labeled anomalies, with existing deep approaches being domain-specific. In this work we present Deep SAD, an end-to-end deep methodology for general semi-supervised anomaly detection. We further introduce an information-theoretic framework for deep anomaly detection based on the idea that the entropy of the latent distribution for normal data should be lower than the entropy of the anomalous distribution, which can serve as a theoretical interpretation for our method. In extensive experiments on MNIST, Fashion-MNIST, and CIFAR-10, along with other anomaly detection benchmark datasets, we demonstrate that our method is on par or outperforms shallow, hybrid, and deep competitors, yielding appreciable performance improvements even when provided with only little labeled data." @default.
• W2948079128 created "2019-06-14" @default.
• W2948079128 creator A5014060431 @default.
• W2948079128 creator A5016979661 @default.
• W2948079128 creator A5024149142 @default.
• W2948079128 creator A5053906729 @default.
• W2948079128 creator A5072460783 @default.
• W2948079128 creator A5072994165 @default.
• W2948079128 creator A5091841504 @default.
• W2948079128 date "2019-06-06" @default.
• W2948079128 modified "2023-10-01" @default.
• W2948079128 title "Deep Semi-Supervised Anomaly Detection" @default.
• W2948079128 cites W1479807131 @default.
• W2948079128 cites W1493372406 @default.
• W2948079128 cites W1533861849 @default.
• W2948079128 cites W1538189649 @default.
• W2948079128 cites W1605527784 @default.
• W2948079128 cites W1622922661 @default.
• W2948079128 cites W1836465849 @default.
• W2948079128 cites W1876967670 @default.
• W2948079128 cites W1959608418 @default.
• W2948079128 cites W1966168239 @default.
• W2948079128 cites W1970088130 @default.
• W2948079128 cites W1995875735 @default.
• W2948079128 cites W2025768430 @default.
• W2948079128 cites W2099111195 @default.
• W2948079128 cites W2108384452 @default.
• W2948079128 cites W2108501770 @default.
• W2948079128 cites W2109169614 @default.
• W2948079128 cites W2115627867 @default.
• W2948079128 cites W2118020555 @default.
• W2948079128 cites W2119531440 @default.
• W2948079128 cites W2122646361 @default.
• W2948079128 cites W2122925692 @default.
• W2948079128 cites W2127883478 @default.
• W2948079128 cites W2127979711 @default.
• W2948079128 cites W2132870739 @default.
• W2948079128 cites W2136504847 @default.
• W2948079128 cites W2143559571 @default.
• W2948079128 cites W2165793886 @default.
• W2948079128 cites W2167717760 @default.
• W2948079128 cites W2170823753 @default.
• W2948079128 cites W2296719434 @default.
• W2948079128 cites W2340896621 @default.
• W2948079128 cites W2412510955 @default.
• W2948079128 cites W2516866958 @default.
• W2948079128 cites W2547788783 @default.
• W2948079128 cites W2593634001 @default.
• W2948079128 cites W2621614835 @default.
• W2948079128 cites W2622563070 @default.
• W2948079128 cites W2766736793 @default.
• W2948079128 cites W2766761849 @default.
• W2948079128 cites W2768800090 @default.
• W2948079128 cites W2785885194 @default.
• W2948079128 cites W2786599352 @default.
• W2948079128 cites W2789159078 @default.
• W2948079128 cites W2803697594 @default.
• W2948079128 cites W2883594813 @default.
• W2948079128 cites W2887997457 @default.
• W2948079128 cites W2902227449 @default.
• W2948079128 cites W2904981516 @default.
• W2948079128 cites W2910068345 @default.
• W2948079128 cites W2949848919 @default.
• W2948079128 cites W2949972936 @default.
• W2948079128 cites W2962742960 @default.
• W2948079128 cites W2962845550 @default.
• W2948079128 cites W2962897886 @default.
• W2948079128 cites W2962957157 @default.
• W2948079128 cites W2963045681 @default.
• W2948079128 cites W2963145887 @default.
• W2948079128 cites W2963226019 @default.
• W2948079128 cites W2963344330 @default.
• W2948079128 cites W2963376662 @default.
• W2948079128 cites W2963739978 @default.
• W2948079128 cites W2963773039 @default.
• W2948079128 cites W2963956526 @default.
• W2948079128 cites W2963982496 @default.
• W2948079128 cites W2964032056 @default.
• W2948079128 cites W2964034630 @default.
• W2948079128 cites W2964121744 @default.
• W2948079128 cites W2964160479 @default.
• W2948079128 cites W2964184826 @default.
• W2948079128 cites W2979454998 @default.
• W2948079128 cites W2989929945 @default.
• W2948079128 cites W3023786531 @default.
• W2948079128 cites W3137695714 @default.
• W2948079128 cites W830076066 @default.
• W2948079128 cites W1857789879 @default.
• W2948079128 hasPublicationYear "2019" @default.
• W2948079128 type Work @default.
• W2948079128 sameAs 2948079128 @default.
• W2948079128 citedByCount "11" @default.
• W2948079128 countsByYear W29480791282019 @default.
• W2948079128 countsByYear W29480791282020 @default.
• W2948079128 countsByYear W29480791282021 @default.
• W2948079128 crossrefType "posted-content" @default.
• W2948079128 hasAuthorship W2948079128A5014060431 @default.
• W2948079128 hasAuthorship W2948079128A5016979661 @default.
• W2948079128 hasAuthorship W2948079128A5024149142 @default.
• W2948079128 hasAuthorship W2948079128A5053906729 @default.

• next