DeepCaps: Going Deeper with Capsule Networks
Abstract
Capsule Network is a promising concept in deep learning, yet its true potential is not fully realized thus far, providing sub-par performance on several key benchmark datasets with complex data. Drawing intuition from the success achieved by Convolutional Neural Networks (CNNs) by going deeper, we introduce DeepCaps1, a deep capsule network architecture which uses a novel 3D convolution based dynamic routing algorithm. With DeepCaps, we surpass the state-of-the-art results in the capsule network domain on CIFAR10, SVHN and Fashion MNIST, while achieving a 68% reduction in the number of parameters. Further, we propose a class-independent decoder network, which strengthens the use of reconstruction loss as a regularization term. This leads to an interesting property of the decoder, which allows us to identify and control the physical attributes of the images represented by the instantiation parameters.
Cite
@article{arxiv.1904.09546,
title = {DeepCaps: Going Deeper with Capsule Networks},
author = {Jathushan Rajasegaran and Vinoj Jayasundara and Sandaru Jayasekara and Hirunima Jayasekara and Suranga Seneviratne and Ranga Rodrigo},
journal= {arXiv preprint arXiv:1904.09546},
year = {2019}
}