Variational Capsule Encoder
This work addresses representation learning for image data, but it is incremental as it combines existing capsule networks with variational auto-encoders in a new way.
The paper tackled the problem of learning better feature representations in latent space by proposing a capsule network-based variational encoder (B-Caps) that modulates the sampling distribution, resulting in improved reconstruction and classification performances on MNIST and Fashion-MNIST datasets, with separation of classes in latent space.
We propose a novel capsule network based variational encoder architecture, called Bayesian capsules (B-Caps), to modulate the mean and standard deviation of the sampling distribution in the latent space. We hypothesized that this approach can learn a better representation of features in the latent space than traditional approaches. Our hypothesis was tested by using the learned latent variables for image reconstruction task, where for MNIST and Fashion-MNIST datasets, different classes were separated successfully in the latent space using our proposed model. Our experimental results have shown improved reconstruction and classification performances for both datasets adding credence to our hypothesis. We also showed that by increasing the latent space dimension, the proposed B-Caps was able to learn a better representation when compared to the traditional variational auto-encoders (VAE). Hence our results indicate the strength of capsule networks in representation learning which has never been examined under the VAE settings before.