… a new image classification task called Top-2 classification to … image samples same as the
traditional image classification … capsule network with k-means routing for text classification. …

… The capsule network (CapsNet) architecture is an attempt to overcome this drawback by
nesting several neural layers within a capsule, connected by dynamic routing, both to identify …

… The original Capsule network has also a set of fully connected layers, referred to as the …
inputs, and try to reconstruct the original image, with the aim of forcing the network to capture real …

… However, the original capsule network is not suitable for some classification tasks, where the
… -scale capsule network that is more robust and efficient for feature representation in image …

… 3.1 Network Design To extract the multi-scale features with the capsule network and keep
the reliability of the network, we develop a multi-scale convolutional capsule network which is …

… neural networks to resolve the problem of viewpoint variations in image classification tasks.
… make use of a capsule neural network to exploit more potential features for image SR. In this …

… And, on the capsule network on medical image related paper to investigate what factors in
those models are essential to the final result and the gaps they haven’t included in their work. …

… it dual-channel capsule network (DCCapsNet). The proposed network will extract spectral
… Then, the network will feed the features into the capsule layers and produce a label for the …

… X-ray images is difficult because of limited resources and heavy burden on the medical system.
To meet the challenge, we propose a capsule network … from chest Xray images. The MHA-…

… 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 …