Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟯𝟵𝟬 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 Momentum Capsule Networks by University of Innsbruck, Austria Follow me for a similar post: Ashish Patel ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 Paper: Momentum Capsule Networks 🔸 This paper is published arxiv2022. 🔸 Introduced in this paper Momentum Capsule Networks (MoCapsNet), a new capsule network architecture that implements residual blocks using capsule layers, which can be used to construct reversible building blocks. Through the use of reversible subnetworks, we have obtained a network that has a much smaller memory footprint than its non-invertible counterpart. ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Capsule networks are a class of neural networks that achieved promising results on many computer vision tasks. 🔹However, baseline capsule networks have failed to reach state-of-the-art results on more complex datasets due to the high computation and memory requirements. 🔸We tackle this problem by proposing a new network architecture, called Momentum Capsule Network (MoCapsNet). 🔹MoCapsNets are inspired by Momentum ResNets, a type of network that applies reversible residual building blocks. 🔸Reversible networks allow for recalculating activations of the forward pass in the backpropagation algorithm, so those memory requirements can be drastically reduced. 🔹In this paper, we provide a framework on how invertible residual building blocks can be applied to capsule networks. We will show that MoCapsNet beats the accuracy of baseline capsule networks on MNIST, SVHN and CIFAR-10 while using considerably less memory. #computervision #artificialintelligence #innovation