… 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 …

Capsule networks can be considered to be the next era of deep learning and have … in supervised
classification. Instead of using scalar values to represent features, the capsule networks …

… To solve the problem of lack of spatial information in CNNs, the Capsule network takes the
form of vectors that convey location transformation information. This article proposes using a …

… networks (CNNs) in automatic image processing has been decisive for the progress and
evolution of remote sensing (RS) hyperspectral imaging (HSI) processing. … in HSI classification. …

… The flexibility of CNN structure make it suitable for computer vision applications, such as
images classification and objects detection [17], [18]. In HSIs classification, CNNs also hold …

… Recalling the original formulation in [47], a layer of a capsule network is divided into … , “Hyperspectral
image classification with capsule network using limited training samples,” Sensors., …

… capsule network (CapsNet), which is a novel network architecture that uses a group of neurons
as a capsule … features in an image and is a more effective image recognition algorithm, …

… issues, we proposed a multiscale capsule network (Ms-CapsNet) … image recognition task.
In this letter, we introduce the self-attention mechanism into the SAR image change detection …

… to improve the HSI classification performance with few training samples. In the proposed
network, a new discriminator is designed by exploiting capsule network (CapsNet) and …

… Our network extracts the spectral and spatial features separately using two convolution …
named it dual-channel capsule network (DCCapsNet). The proposed network will extract spectral …