.png){kind=icon}
.png){kind=icon}
Return
Deep Tensor Capsule Network
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2020.2996282.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Capsule network is a promising model in computer vision. It has achieved excellent results on simple datasets such as MNIST, but the performance deteriorates as data becomes complicated. In order to address this issue, we propose a deep capsule network in this paper. To deepen the capsule network, we present a new tensor capsule based routing algorithm and the corresponding convolution operation. Compared to vector capsules, tensor capsules can capture more instance-level information. Together, the relevant convolution operation is beneficial for reducing the amount of parameters in the routing process. Furthermore, we propose a dropout mechanism for vectors and tensors in order to alleviate the potential overfitting problem. Finally, we also inject the multi-scale capsules of the middle layers into a multi-scale decoder to pursue more details of an image and more clear reconstructed image. Experimental results on CIFAR10, Fashion-MNIST, and SVHN demonstrate that the proposed deep tensor network can achieve very competitive performance compared to other state-of-the-art capsule networks.
Keywords:
Tensile stress
Routing
Convolution
Image reconstruction
Decoding
Heuristic algorithms
Kernel
Capsule network
dynamic routing
dropout
CNNs
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.