Modern day computer vision tasks requires efficient solution to problems such as image
recognition, natural language processing, object detection, object segmentation and …

Over the past few years, the computer vision domain has evolved and made a revolutionary
transition from human-engineered features to automated features to address challenging …

Most capsule network designs rely on traditional matrix multiplication between capsule
layers and computationally expensive routing mechanisms to deal with the capsule …

Modern day computer vision tasks requires efficient solution to problems such as image
recognition, natural language processing, object detection, object segmentation and …

Convolutional neural networks (CNNs) have shown outstanding image classification
performance, having been successfully applied in several real‐world applications. However …

Numerous advancements in various fields, including pattern recognition and image
classification, have been made thanks to modern computer vision and machine learning …

Capsule Network (CapsNet) is a novel structure for deep neural network, map** the
region of target instance to vectors and matrices rather than scalars. This process is enabled …

We introduce multi-lane capsule networks (MLCN), which are a separable and resource
efficient organization of capsule networks (CapsNet) that allows parallel processing while …

We propose a new regularization term for CapsNet that significantly improves the
generalization power of the original method from small training data while requiring much …

In this paper, a novel quaternion-valued (QV) capsule module is designed to construct QV
capsule networks for image classification. The quaternion algebra is introduced into the …