Deep multi-prototype capsule networks

arXiv:2404.15445v1 Announce Type: new
Abstract: Capsule networks are a type of neural network that identify image parts and form the instantiation parameters of a whole hierarchically. The goal behind the network is to perform an inverse computer graphics task, and the network parameters are the mapping weights that transform parts into a whole. The trainability of capsule networks in complex data with high intra-class or intra-part variation is challenging. This paper presents a multi-prototype architecture for guiding capsule networks to …

abstract arxiv capsule computer computer graphics cs.cv cs.ne form graphics identify image mapping network networks neural network parameters type