Faster Multiscale Capsule Network With Octave Convolution for Hyperspectral Image Classification

Recently proposed capsule networks have revealed powerfulness in various visual tasks. However, the traditional CNNs adopted in the capsule layer of the capsule network have the problem of high parameter redundancy. In this letter, we propose a faster multiscale capsule network with octave convolution (MSOctCaps) for hyperspectral image classification. In the proposed MSOctCaps, we design multiple kernels of different sizes with parallel convolution to extract deep multiscale features. To feasibly reduce the redundancy of parameters and achieve high accuracy, the octave convolution is explored in the capsule layer, instead of the traditional convolution, which improves the accuracy of the capsule layer above predicted by the capsule layer below. The comparison experiments with six state-of-the-arts on two challenging contest data sets demonstrate the proposed MSOctCaps is able to produce competitive advantages in terms of both classification accuracy and computational time.

Automated summary

The study proposes a faster multiscale capsule network with octave convolution for hyperspectral image classification, which reduces parameter redundancy and improves accuracy. The novel approach demonstrates competitive advantages in both classification accuracy and computational time compared to existing methods.