An Effective Hit-or-Miss Layer Favoring Feature Interpretation as Learned Prototypes Deformations
This work addresses interpretability in neural networks for classification tasks, offering a hybrid data augmentation method, but it is incremental as it builds on existing capsule network architectures.
The authors tackled the problem of uninterpretable black-box neural networks by redesigning a capsule network with a novel Hit-or-Miss layer to synthesize class-representative prototypes, resulting in better performance than the initial CapsNet on several datasets while enabling visualization of features as prototype deformations.
Neural networks designed for the task of classification have become a commodity in recent years. Many works target the development of more effective networks, which results in a complexification of their architectures with more layers, multiple sub-networks, or even the combination of multiple classifiers, but this often comes at the expense of producing uninterpretable black boxes. In this paper, we redesign a simple capsule network to enable it to synthesize class-representative samples, called prototypes, by replacing the last layer with a novel Hit-or-Miss layer. This layer contains activated vectors, called capsules, that we train to hit or miss a fixed target capsule by tailoring a specific centripetal loss function. This possibility allows to develop a data augmentation step combining information from the data space and the feature space, resulting in a hybrid data augmentation process. We show that our network, named HitNet, is able to reach better performances than those reproduced with the initial CapsNet on several datasets, while allowing to visualize the nature of the features extracted as deformations of the prototypes, which provides a direct insight into the feature representation learned by the network .