… , in this study, we considered a deeper capsule network based on CapsNet with more layers
to solve the problem of limited labeled samples in the HSI classification. In this section, we …

… classification of HSIs while significantly reducing the network design complexity. Specifically,
based on Hinton’s capsule networks, … that redefines the concept of capsule units to become …

… of hyperspectral image (HSI) classification. In particular, convolutional neural networks (CNNs)
have … Recently, a novel type of neural networks called capsule networks (CapsNets) was …

… Despite the effectiveness of DL in single-modality-dominated classification tasks… sensing
image classification problems using multimodal input. This study uses fully connected networks (…

… fields such as object recognition, image classification, and speech recognition [7]. In the
field of remote sensing, CNN has also been widely used for the accurate classification of crop, …

… The convolutional neural network (CNN) is widely used for image classification because of
… in remote sensing (RS) scene classification is that the size of data set is small and images in …

… image and optical image change detection is proposed, which is based on a pixel-level
mapping method and a capsule network … performance in image processing. In the task of change …

… Keeping in view the importance of properties of the remote images, the Capsule network …
a deep understanding of the remote sensing images in hyperspectral image classification [34]. …

… In this paper, a new HSI classification framework based on Capsule Network (CapsNet) is
… framework, aiming to train convolutional layers and capsule layers, respectively. In addition, …

… deeper, we will further consider a deeper capsule network with more layers to explore the
potential of capsule architecture in HSI classification. In addition, a local connection instead of …