Developments in Capsule Network Architecture: A Review

Abstract

AbstractProblems like image recognition, object detection, image segmentation need efficacious solution for computer vision. Traditionally, these problems are being solved by Deep Learning. Convolutional Neural Network(CNN) and Recurrent Neural Network models are used for computer vision tasks. However, CNNs have some drawbacks. They cannot recognize objects if same object is viewed from different viewpoints and deformed objects. Besides, CNNs require an immense amount of training data. Capsule networks are viewed as a new solution for computer vision problems. They are capable of solving the above-mentioned problems better than CNNs. Capsule networks have shown better accuracy in many computer vision applications. In this paper, we review the methodologies and architectures of existing implementations of capsule networks.KeywordsDeep learningCNNDynamic routingCapsule networkExpectation maximization