FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308331014> ?p ?o ?g. }

• W4308331014 endingPage "5555" @default.
• W4308331014 startingPage "5555" @default.
• W4308331014 abstract "Hyperspectral anomaly detection is a popular research direction for hyperspectral images; however, it is problematic because it separates the background and anomaly without prior target information. Currently, deep neural networks are used as an extractor to mine intrinsic features in hyperspectral images, which can be fed into separate anomaly detection methods to improve their performances. However, this hybrid approach is suboptimal because the subsequent detector is unable to drive the data representation in hidden layers, which makes it a challenge to maximize the capabilities of deep neural networks when extracting the underlying features customized for anomaly detection. To address this issue, a novel unsupervised, self-attention-based, one-class neural network (SAOCNN) is proposed in this paper. SAOCNN consists of two components: a novel feature extraction network and a one-class SVM (OC-SVM) anomaly detection method, which are interconnected and jointly trained by the OC-SVM-like loss function. The adoption of co-training updates the feature extraction network together with the anomaly detector, thus improving the whole network’s detection performance. Considering that the prominent feature of an anomaly lies in its difference from the background, we designed a deep neural extraction network to learn more comprehensive hyperspectral image features, including spectral, global correlation, and local spatial features. To accomplish this goal, we adopted an adversarial autoencoder to produce the residual image with highlighted anomaly targets and a suppressed background, which is input into an improved non-local module to adaptively select the useful global information in the whole deep feature space. In addition, we incorporated a two-layer convolutional network to obtain local features. SAOCNN maps the original hyperspectral data to a learned feature space with better anomaly separation from the background, making it possible for the hyperplane to separate them. Our experiments on six public hyperspectral datasets demonstrate the state-of-the-art performance and superiority of our proposed SAOCNN when extracting deep potential features, which are more conducive to anomaly detection." @default.
• W4308331014 created "2022-11-11" @default.
• W4308331014 creator A5005867726 @default.
• W4308331014 creator A5061929348 @default.
• W4308331014 creator A5063350278 @default.
• W4308331014 creator A5068193499 @default.
• W4308331014 date "2022-11-03" @default.
• W4308331014 modified "2023-10-06" @default.
• W4308331014 title "SAOCNN: Self-Attention and One-Class Neural Networks for Hyperspectral Anomaly Detection" @default.
• W4308331014 cites W1970088130 @default.
• W4308331014 cites W1971358070 @default.
• W4308331014 cites W1981939910 @default.
• W4308331014 cites W1988177629 @default.
• W4308331014 cites W2001298088 @default.
• W4308331014 cites W2001338493 @default.
• W4308331014 cites W2040078680 @default.
• W4308331014 cites W2047519171 @default.
• W4308331014 cites W2047870694 @default.
• W4308331014 cites W2054804828 @default.
• W4308331014 cites W2063102607 @default.
• W4308331014 cites W2086506050 @default.
• W4308331014 cites W2097381359 @default.
• W4308331014 cites W2100495367 @default.
• W4308331014 cites W2122646361 @default.
• W4308331014 cites W2124463804 @default.
• W4308331014 cites W2140475713 @default.
• W4308331014 cites W2142552707 @default.
• W4308331014 cites W2158340226 @default.
• W4308331014 cites W2163129097 @default.
• W4308331014 cites W2165447611 @default.
• W4308331014 cites W2415846130 @default.
• W4308331014 cites W2737771677 @default.
• W4308331014 cites W2740976805 @default.
• W4308331014 cites W2772452219 @default.
• W4308331014 cites W2790159988 @default.
• W4308331014 cites W2796629918 @default.
• W4308331014 cites W2800662010 @default.
• W4308331014 cites W2903882147 @default.
• W4308331014 cites W2948363198 @default.
• W4308331014 cites W2949343319 @default.
• W4308331014 cites W2962898849 @default.
• W4308331014 cites W2963091558 @default.
• W4308331014 cites W2987833009 @default.
• W4308331014 cites W2998142089 @default.
• W4308331014 cites W3003955104 @default.
• W4308331014 cites W3038308280 @default.
• W4308331014 cites W3087931076 @default.
• W4308331014 cites W3112715721 @default.
• W4308331014 cites W3176520651 @default.
• W4308331014 cites W3202896130 @default.
• W4308331014 cites W4212884756 @default.
• W4308331014 cites W4233367343 @default.
• W4308331014 cites W4235713725 @default.
• W4308331014 cites W4250482878 @default.
• W4308331014 cites W4312835785 @default.
• W4308331014 doi "https://doi.org/10.3390/rs14215555" @default.
• W4308331014 hasPublicationYear "2022" @default.
• W4308331014 type Work @default.
• W4308331014 citedByCount "0" @default.
• W4308331014 crossrefType "journal-article" @default.
• W4308331014 hasAuthorship W4308331014A5005867726 @default.
• W4308331014 hasAuthorship W4308331014A5061929348 @default.
• W4308331014 hasAuthorship W4308331014A5063350278 @default.
• W4308331014 hasAuthorship W4308331014A5068193499 @default.
• W4308331014 hasBestOaLocation W43083310141 @default.
• W4308331014 hasConcept C101738243 @default.
• W4308331014 hasConcept C121332964 @default.
• W4308331014 hasConcept C12267149 @default.
• W4308331014 hasConcept C12997251 @default.
• W4308331014 hasConcept C138885662 @default.
• W4308331014 hasConcept C153180895 @default.
• W4308331014 hasConcept C154945302 @default.
• W4308331014 hasConcept C159078339 @default.
• W4308331014 hasConcept C26873012 @default.
• W4308331014 hasConcept C2776401178 @default.
• W4308331014 hasConcept C41008148 @default.
• W4308331014 hasConcept C41895202 @default.
• W4308331014 hasConcept C50644808 @default.
• W4308331014 hasConcept C52622490 @default.
• W4308331014 hasConcept C59404180 @default.
• W4308331014 hasConcept C739882 @default.
• W4308331014 hasConceptScore W4308331014C101738243 @default.
• W4308331014 hasConceptScore W4308331014C121332964 @default.
• W4308331014 hasConceptScore W4308331014C12267149 @default.
• W4308331014 hasConceptScore W4308331014C12997251 @default.
• W4308331014 hasConceptScore W4308331014C138885662 @default.
• W4308331014 hasConceptScore W4308331014C153180895 @default.
• W4308331014 hasConceptScore W4308331014C154945302 @default.
• W4308331014 hasConceptScore W4308331014C159078339 @default.
• W4308331014 hasConceptScore W4308331014C26873012 @default.
• W4308331014 hasConceptScore W4308331014C2776401178 @default.
• W4308331014 hasConceptScore W4308331014C41008148 @default.
• W4308331014 hasConceptScore W4308331014C41895202 @default.
• W4308331014 hasConceptScore W4308331014C50644808 @default.
• W4308331014 hasConceptScore W4308331014C52622490 @default.
• W4308331014 hasConceptScore W4308331014C59404180 @default.
• W4308331014 hasConceptScore W4308331014C739882 @default.
• W4308331014 hasFunder F4320335787 @default.

• next