Zobrazeno 1 - 10
of 4 546
pro vyhledávání: '"Hyperspectral image (HSI) classification"'
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 18, Pp 1329-1344 (2025)
Domain adaptation has been proven effective for addressing cross-domain hyperspectral image (HSI) classification, especially when the target domain has no labeled samples. Current domain adaptation algorithms focus on finding domain-invariant subspac
Externí odkaz:
https://doaj.org/article/4a211016184347d196986592a375af8b
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 18, Pp 112-131 (2025)
Hyperspectral image (HSI) classification is a challenging task in remote sensing applications, aiming to determine the category of each pixel by utilizing rich spectral and spatial information in HSI. Convolutional neural networks (CNNs) have been ef
Externí odkaz:
https://doaj.org/article/e87fcdd975e74ecbbcd27b68cfc077c1
Autor:
Zhu, Xing-Hui1 (AUTHOR) zhuxh@hunau.net, Li, Kai-Run1 (AUTHOR) viperl1@stu.hunau.edu.cn, Deng, Yang-Jun1 (AUTHOR) dyj2012@yeah.net, Long, Chen-Feng1 (AUTHOR) tsq@hunau.edu.cn, Wang, Wei-Ye2 (AUTHOR) wwy@cuit.edu.cn, Tan, Si-Qiao1 (AUTHOR)
Publikováno v:
Remote Sensing. Nov2024, Vol. 16 Issue 21, p4055. 22p.
Autor:
Bai, Yu1 (AUTHOR), Liu, Dongmin1 (AUTHOR), Zhang, Lili1 (AUTHOR) lily_zhang@sau.edu.cn, Wu, Haoqi1 (AUTHOR)
Publikováno v:
Sensors (14248220). Oct2024, Vol. 24 Issue 20, p6647. 31p.
Publikováno v:
IEEE Access, Vol 12, Pp 173076-173090 (2024)
In hyperspectral image (HSI) classification, combining the strengths of convolutional neural networks (CNNs) and Transformers can significantly enhance classification performance and model robustness. However, neural networks that combine CNNs and Tr
Externí odkaz:
https://doaj.org/article/8e0407c34cd0480a889fa733151482ac
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 17, Pp 17207-17220 (2024)
The multilayer perceptron (MLP) has gained widespread popularity and demonstrated outstanding performance in hyperspectral image (HSI) classification in recent years. However, the native MLP architecture and its variants are insufficient in expressin
Externí odkaz:
https://doaj.org/article/f8f21ba4c4a84e5d92276453dcbc203c
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 17, Pp 16876-16889 (2024)
Significant progress has been achieved in hyperspectral image (HSI) classification research through the application of the transformer blocks. Despite transformers possess strong long-range dependence modeling capabilities, they primarily extract non
Externí odkaz:
https://doaj.org/article/f9538964dfa8458fa80e70892b114b62
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 17, Pp 15393-15406 (2024)
In recent years, deep learning algorithms, particularly convolutional neural networks, have significantly improved the performance of the hyperspectral image (HSI) classification. However, due to the high dimensionality of HSI and limited training sa
Externí odkaz:
https://doaj.org/article/6dc29576d5e44f1e892cda65acf58d37
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 17, Pp 14486-14501 (2024)
Deep learning is an effective method for hyperspectral image (HSI) classification, where CNN-based and Transformer-based methods have achieved excellent performance. However, there are some drawbacks to the existing CNN-based and Transformer-based HS
Externí odkaz:
https://doaj.org/article/922577d4c4144006b93ac0f55dcb429f
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 17, Pp 14521-14542 (2024)
Convolutional neural network (CNN) and transformer-based models have been widely used in hyperspectral image (HSI) classification due to their excellent local and global modeling capabilities. In addition, attention mechanism is widely embedded in th
Externí odkaz:
https://doaj.org/article/5e0126c779c1402a8521276a503d5888