TraceCaps: A Capsule-based Neural Network for Semantic Segmentation
This work addresses semantic segmentation for computer vision applications, offering an incremental improvement over existing FCN solutions by incorporating capsule layers for better interpretability and performance.
The paper tackles semantic segmentation by proposing a capsule-based neural network that leverages part-whole dependencies to derive class probabilities through a traceback pipeline, resulting in enhanced segmentation performance on modified MNIST and neuroimages compared to leading FCN variants.
In this paper, we propose a capsule-based neural network model to solve the semantic segmentation problem. By taking advantage of the extractable part-whole dependencies available in capsule layers, we derive the probabilities of the class labels for individual capsules through a recursive, layer-by-layer procedure. We model this procedure as a traceback pipeline and take it as a central piece to build an end-to-end segmentation network. Under the proposed framework, image-level class labels and object boundaries are jointly sought in an explicit manner, which poses a significant advantage over the state-of-the-art fully convolutional network (FCN) solutions. With the capability to extracted part-whole information, our traceback pipeline can potentially be utilized as the building blocks to design interpretable neural networks. Experiments conducted on modified MNIST and neuroimages demonstrate that our model considerably enhance the segmentation performance compared to the leading FCN variants.