DeepCaps: Going Deeper with Capsule Networks
This work addresses performance limitations in capsule networks for computer vision tasks, representing an incremental improvement with specific gains.
The authors tackled the problem of capsule networks underperforming on complex datasets by introducing DeepCaps, a deep architecture with a novel 3D convolution-based dynamic routing algorithm, which achieved state-of-the-art results on CIFAR10, SVHN, and Fashion MNIST while reducing parameters by 68%.
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.