Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385945263> ?p ?o ?g. }
- W4385945263 endingPage "17" @default.
- W4385945263 startingPage "1" @default.
- W4385945263 abstract "Recently, deep learning methods have demonstrated their potentials in extracting spectral information for hyperspectral images and have been widely applied in hyperspectral target detection (HTD). However, prior deep learning methods, represented by the convolutional neural networks, mainly focus on the local information and representation, which cannot well capture the long-range dependence. Besides, limited target references cannot meet the need of massive labelled samples for the training process. This work develops a triplet spectral-wise transformer-based target detector (TSTTD) to deal with these problems. First, this work explores a novel triplet spectral-wise transformer network for HTD task, and a data augmentation method is utilized to construct sufficient and balanced training samples for balanced learning. The proposed network shows advantages in learning local features from multiple adjacent bands and global features with long-range dependence. Second, for improving the separability between targets and backgrounds, a novel inter-category separation and intra-category aggregation (ISIA) loss function is proposed, which joints the hard-negative-mining triplet loss and the binary cross entropy loss. Third, experimental results on six data sets show that our proposed method is effective in leading to excellent detection performance when compared with other state-of-the-art methods." @default.
- W4385945263 created "2023-08-18" @default.
- W4385945263 creator A5025615156 @default.
- W4385945263 creator A5074772585 @default.
- W4385945263 creator A5079556851 @default.
- W4385945263 date "2023-01-01" @default.
- W4385945263 modified "2023-10-17" @default.
- W4385945263 title "Triplet Spectralwise Transformer Network for Hyperspectral Target Detection" @default.
- W4385945263 cites W1799946925 @default.
- W4385945263 cites W1869500417 @default.
- W4385945263 cites W1899348529 @default.
- W4385945263 cites W1955055330 @default.
- W4385945263 cites W1975517671 @default.
- W4385945263 cites W1986921156 @default.
- W4385945263 cites W2009539575 @default.
- W4385945263 cites W2037328426 @default.
- W4385945263 cites W2041709052 @default.
- W4385945263 cites W2067782748 @default.
- W4385945263 cites W2075295413 @default.
- W4385945263 cites W2086119276 @default.
- W4385945263 cites W2096972831 @default.
- W4385945263 cites W2110211064 @default.
- W4385945263 cites W2123817565 @default.
- W4385945263 cites W2125341398 @default.
- W4385945263 cites W2144158572 @default.
- W4385945263 cites W2154236340 @default.
- W4385945263 cites W2157364932 @default.
- W4385945263 cites W2194775991 @default.
- W4385945263 cites W2520774990 @default.
- W4385945263 cites W2612112834 @default.
- W4385945263 cites W2740976805 @default.
- W4385945263 cites W2907100627 @default.
- W4385945263 cites W2915888826 @default.
- W4385945263 cites W2921084751 @default.
- W4385945263 cites W2951039757 @default.
- W4385945263 cites W2952956606 @default.
- W4385945263 cites W2953277363 @default.
- W4385945263 cites W2953308875 @default.
- W4385945263 cites W2963026686 @default.
- W4385945263 cites W2963351448 @default.
- W4385945263 cites W2971698117 @default.
- W4385945263 cites W2985741321 @default.
- W4385945263 cites W2997043451 @default.
- W4385945263 cites W3011095215 @default.
- W4385945263 cites W3021150190 @default.
- W4385945263 cites W3037306899 @default.
- W4385945263 cites W3082142378 @default.
- W4385945263 cites W3097141235 @default.
- W4385945263 cites W3098024612 @default.
- W4385945263 cites W3099206234 @default.
- W4385945263 cites W3100011500 @default.
- W4385945263 cites W3128776197 @default.
- W4385945263 cites W3140885850 @default.
- W4385945263 cites W3154634026 @default.
- W4385945263 cites W3199351457 @default.
- W4385945263 cites W3212625467 @default.
- W4385945263 cites W3214821343 @default.
- W4385945263 cites W4210794570 @default.
- W4385945263 cites W4221010218 @default.
- W4385945263 cites W4225582357 @default.
- W4385945263 cites W4240485910 @default.
- W4385945263 doi "https://doi.org/10.1109/tgrs.2023.3306084" @default.
- W4385945263 hasPublicationYear "2023" @default.
- W4385945263 type Work @default.
- W4385945263 citedByCount "0" @default.
- W4385945263 crossrefType "journal-article" @default.
- W4385945263 hasAuthorship W4385945263A5025615156 @default.
- W4385945263 hasAuthorship W4385945263A5074772585 @default.
- W4385945263 hasAuthorship W4385945263A5079556851 @default.
- W4385945263 hasConcept C106301342 @default.
- W4385945263 hasConcept C108583219 @default.
- W4385945263 hasConcept C121332964 @default.
- W4385945263 hasConcept C153180895 @default.
- W4385945263 hasConcept C154945302 @default.
- W4385945263 hasConcept C159078339 @default.
- W4385945263 hasConcept C165801399 @default.
- W4385945263 hasConcept C167981619 @default.
- W4385945263 hasConcept C33923547 @default.
- W4385945263 hasConcept C41008148 @default.
- W4385945263 hasConcept C48372109 @default.
- W4385945263 hasConcept C50644808 @default.
- W4385945263 hasConcept C59404180 @default.
- W4385945263 hasConcept C62520636 @default.
- W4385945263 hasConcept C66322947 @default.
- W4385945263 hasConcept C76155785 @default.
- W4385945263 hasConcept C81363708 @default.
- W4385945263 hasConcept C94375191 @default.
- W4385945263 hasConcept C94915269 @default.
- W4385945263 hasConceptScore W4385945263C106301342 @default.
- W4385945263 hasConceptScore W4385945263C108583219 @default.
- W4385945263 hasConceptScore W4385945263C121332964 @default.
- W4385945263 hasConceptScore W4385945263C153180895 @default.
- W4385945263 hasConceptScore W4385945263C154945302 @default.
- W4385945263 hasConceptScore W4385945263C159078339 @default.
- W4385945263 hasConceptScore W4385945263C165801399 @default.
- W4385945263 hasConceptScore W4385945263C167981619 @default.
- W4385945263 hasConceptScore W4385945263C33923547 @default.
- W4385945263 hasConceptScore W4385945263C41008148 @default.