Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313137072> ?p ?o ?g. }
- W4313137072 endingPage "9841" @default.
- W4313137072 startingPage "9829" @default.
- W4313137072 abstract "Hyperspectral anomaly detection (HAD) aims at detecting the anomalies without any prerequisite information, which gains lots of attention in recent years. Most of existing detectors locate the anomalies by eliminating the background. The background is usually reconstructed by utilizing only the global and local homogenous attribute, no matter the matrix decomposition-based or the deep learning-based methods. In this article, a dynamic negative sampling autoencoder is proposed for the hyperspectral anomaly detection (DNA-HAD). Some pixels are randomly selected and altered as negative samples. Both the rest original pixels and the altered negative samples are sent into the network. An adaptive adjusted loss function is designed to suppress the reconstruction error for the original pixels, and to enlarge the error for the negative samples. Meanwhile, skip connection is designed to ensure features at both shallow levels and deep levels being utilized for the reconstructing process. In this way, by importing some negative samples in the reconstructing process, the proposed DNA-HAD is not only robust to reconstruct the background but also sensitive to detect the anomalies. Experiments on six hyperspectral imagery which are captured by different sensors have demonstrated the effectiveness of the proposed method." @default.
- W4313137072 created "2023-01-06" @default.
- W4313137072 creator A5011047259 @default.
- W4313137072 creator A5034520275 @default.
- W4313137072 creator A5039228563 @default.
- W4313137072 creator A5061974899 @default.
- W4313137072 date "2022-01-01" @default.
- W4313137072 modified "2023-10-15" @default.
- W4313137072 title "Dynamic Negative Sampling Autoencoder for Hyperspectral Anomaly Detection" @default.
- W4313137072 cites W2004491663 @default.
- W4313137072 cites W2024288510 @default.
- W4313137072 cites W2040078680 @default.
- W4313137072 cites W2047870694 @default.
- W4313137072 cites W2067897118 @default.
- W4313137072 cites W2141014056 @default.
- W4313137072 cites W2424277038 @default.
- W4313137072 cites W2497075055 @default.
- W4313137072 cites W2740976805 @default.
- W4313137072 cites W2884436604 @default.
- W4313137072 cites W2898121906 @default.
- W4313137072 cites W2900199428 @default.
- W4313137072 cites W2949343319 @default.
- W4313137072 cites W2955133371 @default.
- W4313137072 cites W2969635036 @default.
- W4313137072 cites W2972480129 @default.
- W4313137072 cites W2975506318 @default.
- W4313137072 cites W3000775737 @default.
- W4313137072 cites W3003955104 @default.
- W4313137072 cites W3005109735 @default.
- W4313137072 cites W3007076381 @default.
- W4313137072 cites W3008839601 @default.
- W4313137072 cites W3011095215 @default.
- W4313137072 cites W3023089620 @default.
- W4313137072 cites W3028138626 @default.
- W4313137072 cites W3042747521 @default.
- W4313137072 cites W3080792885 @default.
- W4313137072 cites W3112037842 @default.
- W4313137072 cites W3112619358 @default.
- W4313137072 cites W3123995827 @default.
- W4313137072 cites W3137199127 @default.
- W4313137072 cites W3153686193 @default.
- W4313137072 cites W3158390871 @default.
- W4313137072 cites W3160949528 @default.
- W4313137072 cites W3165733160 @default.
- W4313137072 cites W3171001481 @default.
- W4313137072 cites W3181727745 @default.
- W4313137072 cites W3186256209 @default.
- W4313137072 cites W3199351457 @default.
- W4313137072 cites W3200993454 @default.
- W4313137072 cites W3204653398 @default.
- W4313137072 cites W3211879038 @default.
- W4313137072 cites W4200272877 @default.
- W4313137072 cites W4212800897 @default.
- W4313137072 cites W4214751062 @default.
- W4313137072 cites W4214816856 @default.
- W4313137072 cites W4226048297 @default.
- W4313137072 cites W4285085921 @default.
- W4313137072 doi "https://doi.org/10.1109/jstars.2022.3220514" @default.
- W4313137072 hasPublicationYear "2022" @default.
- W4313137072 type Work @default.
- W4313137072 citedByCount "0" @default.
- W4313137072 crossrefType "journal-article" @default.
- W4313137072 hasAuthorship W4313137072A5011047259 @default.
- W4313137072 hasAuthorship W4313137072A5034520275 @default.
- W4313137072 hasAuthorship W4313137072A5039228563 @default.
- W4313137072 hasAuthorship W4313137072A5061974899 @default.
- W4313137072 hasBestOaLocation W43131370721 @default.
- W4313137072 hasConcept C101738243 @default.
- W4313137072 hasConcept C106131492 @default.
- W4313137072 hasConcept C108583219 @default.
- W4313137072 hasConcept C121332964 @default.
- W4313137072 hasConcept C12997251 @default.
- W4313137072 hasConcept C140779682 @default.
- W4313137072 hasConcept C153180895 @default.
- W4313137072 hasConcept C154945302 @default.
- W4313137072 hasConcept C159078339 @default.
- W4313137072 hasConcept C160633673 @default.
- W4313137072 hasConcept C26873012 @default.
- W4313137072 hasConcept C31972630 @default.
- W4313137072 hasConcept C41008148 @default.
- W4313137072 hasConcept C739882 @default.
- W4313137072 hasConceptScore W4313137072C101738243 @default.
- W4313137072 hasConceptScore W4313137072C106131492 @default.
- W4313137072 hasConceptScore W4313137072C108583219 @default.
- W4313137072 hasConceptScore W4313137072C121332964 @default.
- W4313137072 hasConceptScore W4313137072C12997251 @default.
- W4313137072 hasConceptScore W4313137072C140779682 @default.
- W4313137072 hasConceptScore W4313137072C153180895 @default.
- W4313137072 hasConceptScore W4313137072C154945302 @default.
- W4313137072 hasConceptScore W4313137072C159078339 @default.
- W4313137072 hasConceptScore W4313137072C160633673 @default.
- W4313137072 hasConceptScore W4313137072C26873012 @default.
- W4313137072 hasConceptScore W4313137072C31972630 @default.
- W4313137072 hasConceptScore W4313137072C41008148 @default.
- W4313137072 hasConceptScore W4313137072C739882 @default.
- W4313137072 hasFunder F4320321001 @default.
- W4313137072 hasLocation W43131370721 @default.
- W4313137072 hasLocation W43131370722 @default.