Capsule networks for low-data transfer learning
This work addresses the challenge of efficient learning with limited data for machine learning practitioners, though it appears incremental as it builds on existing capsule network methods.
The researchers tackled the problem of low-data transfer learning by proposing a capsule network architecture that generalizes to new information over 25 times faster than a similar convolutional neural network, as demonstrated on the multiMNIST dataset with injected missing digits.
We propose a capsule network-based architecture for generalizing learning to new data with few examples. Using both generative and non-generative capsule networks with intermediate routing, we are able to generalize to new information over 25 times faster than a similar convolutional neural network. We train the networks on the multiMNIST dataset lacking one digit. After the networks reach their maximum accuracy, we inject 1-100 examples of the missing digit into the training set, and measure the number of batches needed to return to a comparable level of accuracy. We then discuss the improvement in low-data transfer learning that capsule networks bring, and propose future directions for capsule research.