FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285258034> ?p ?o ?g. }

• W4285258034 endingPage "16" @default.
• W4285258034 startingPage "1" @default.
• W4285258034 abstract "Hyperspectral anomaly detection aims to detect objects significantly different from their surrounding background. Recently, many detectors based on autoencoder (AE) exhibited promising performances in hyperspectral anomaly detection tasks. However, the fundamental hypothesis of the AE-based detector that anomaly is more challenging to be reconstructed than background may not always be true in practice. We demonstrate that an autoencoder could well reconstruct anomalies even without anomalies for training. Because AE models mainly focus on the quality of sample reconstruction and do not care if the encoded features solely represent the background rather than anomalies. If more information is preserved than needed to reconstruct the background, the anomalies will be well reconstructed. This paper proposes a cluster-memory augmented autoencoder via deep optimal transportation clustering (OTCMA) for hyperspectral anomaly detection to solve this problem. The deep clustering method based on optimal transportation is proposed to enhance the features consistency of samples within the same categories and features discrimination of samples in different categories. The memory module stores the background&#x2019;s consistent features, which are the cluster centers for each category background. We retrieve more consistent features from the memory module instead of reconstructing a sample utilizing its own encoded features. The network focuses more on consistent feature reconstruction by training AE with a memory module. This effectively restricts the reconstruction ability of AE and prevents reconstructing anomalies. Extensive experiments on the benchmark datasets demonstrate that our proposed OTCMA achieves state-of-the-art results. Besides, this paper presents further discussions about the effectiveness of our proposed memory module and different criterion for better anomaly detection." @default.
• W4285258034 created "2022-07-14" @default.
• W4285258034 creator A5035508615 @default.
• W4285258034 creator A5049776440 @default.
• W4285258034 creator A5050630882 @default.
• W4285258034 creator A5066376249 @default.
• W4285258034 creator A5085893076 @default.
• W4285258034 date "2022-01-01" @default.
• W4285258034 modified "2023-10-16" @default.
• W4285258034 title "Cluster-Memory Augmented Deep Autoencoder via Optimal Transportation for Hyperspectral Anomaly Detection" @default.
• W4285258034 cites W1970088130 @default.
• W4285258034 cites W1970099214 @default.
• W4285258034 cites W1972344061 @default.
• W4285258034 cites W2004491663 @default.
• W4285258034 cites W2010702969 @default.
• W4285258034 cites W2017014096 @default.
• W4285258034 cites W2024138258 @default.
• W4285258034 cites W2047870694 @default.
• W4285258034 cites W2048976066 @default.
• W4285258034 cites W2049189005 @default.
• W4285258034 cites W2087263574 @default.
• W4285258034 cites W2095416759 @default.
• W4285258034 cites W2097381359 @default.
• W4285258034 cites W2124463804 @default.
• W4285258034 cites W2165447611 @default.
• W4285258034 cites W2167799103 @default.
• W4285258034 cites W2288752886 @default.
• W4285258034 cites W2295576075 @default.
• W4285258034 cites W2321627895 @default.
• W4285258034 cites W2343117455 @default.
• W4285258034 cites W2461725797 @default.
• W4285258034 cites W2547840382 @default.
• W4285258034 cites W2548791488 @default.
• W4285258034 cites W2592141703 @default.
• W4285258034 cites W2740976805 @default.
• W4285258034 cites W2772452219 @default.
• W4285258034 cites W2781778455 @default.
• W4285258034 cites W2796629918 @default.
• W4285258034 cites W2900199428 @default.
• W4285258034 cites W2949079224 @default.
• W4285258034 cites W2963049059 @default.
• W4285258034 cites W2969635036 @default.
• W4285258034 cites W3003955104 @default.
• W4285258034 cites W3005109735 @default.
• W4285258034 cites W3007076381 @default.
• W4285258034 cites W3026303927 @default.
• W4285258034 cites W3097560423 @default.
• W4285258034 cites W3112925912 @default.
• W4285258034 cites W3118889207 @default.
• W4285258034 cites W3124606680 @default.
• W4285258034 cites W3135550350 @default.
• W4285258034 cites W3164855829 @default.
• W4285258034 cites W3183600011 @default.
• W4285258034 cites W3212209618 @default.
• W4285258034 cites W4206471589 @default.
• W4285258034 doi "https://doi.org/10.1109/tgrs.2022.3180548" @default.
• W4285258034 hasPublicationYear "2022" @default.
• W4285258034 type Work @default.
• W4285258034 citedByCount "4" @default.
• W4285258034 countsByYear W42852580342023 @default.
• W4285258034 crossrefType "journal-article" @default.
• W4285258034 hasAuthorship W4285258034A5035508615 @default.
• W4285258034 hasAuthorship W4285258034A5049776440 @default.
• W4285258034 hasAuthorship W4285258034A5050630882 @default.
• W4285258034 hasAuthorship W4285258034A5066376249 @default.
• W4285258034 hasAuthorship W4285258034A5085893076 @default.
• W4285258034 hasConcept C101738243 @default.
• W4285258034 hasConcept C108583219 @default.
• W4285258034 hasConcept C121332964 @default.
• W4285258034 hasConcept C124101348 @default.
• W4285258034 hasConcept C127313418 @default.
• W4285258034 hasConcept C12997251 @default.
• W4285258034 hasConcept C13280743 @default.
• W4285258034 hasConcept C138885662 @default.
• W4285258034 hasConcept C153180895 @default.
• W4285258034 hasConcept C154945302 @default.
• W4285258034 hasConcept C159078339 @default.
• W4285258034 hasConcept C185798385 @default.
• W4285258034 hasConcept C26873012 @default.
• W4285258034 hasConcept C2776401178 @default.
• W4285258034 hasConcept C2776436953 @default.
• W4285258034 hasConcept C41008148 @default.
• W4285258034 hasConcept C41895202 @default.
• W4285258034 hasConcept C73555534 @default.
• W4285258034 hasConcept C739882 @default.
• W4285258034 hasConceptScore W4285258034C101738243 @default.
• W4285258034 hasConceptScore W4285258034C108583219 @default.
• W4285258034 hasConceptScore W4285258034C121332964 @default.
• W4285258034 hasConceptScore W4285258034C124101348 @default.
• W4285258034 hasConceptScore W4285258034C127313418 @default.
• W4285258034 hasConceptScore W4285258034C12997251 @default.
• W4285258034 hasConceptScore W4285258034C13280743 @default.
• W4285258034 hasConceptScore W4285258034C138885662 @default.
• W4285258034 hasConceptScore W4285258034C153180895 @default.
• W4285258034 hasConceptScore W4285258034C154945302 @default.
• W4285258034 hasConceptScore W4285258034C159078339 @default.
• W4285258034 hasConceptScore W4285258034C185798385 @default.
• W4285258034 hasConceptScore W4285258034C26873012 @default.

• next