相关论文: No Routing Needed Between Capsules

Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications. However, the large model sizes of DNNs yield high demands on computation…

We show that unsupervised training of latent capsule layers using only the reconstruction loss, without masking to select the correct output class, causes a loss of equivariances and other desirable capsule qualities. This implies that…

We introduce Multi-Lane Capsule Networks (MLCN), which are a separable and resource efficient organization of Capsule Networks (CapsNet) that allows parallel processing, while achieving high accuracy at reduced cost. A MLCN is composed of a…

CoVariance Neural Networks (VNNs) perform graph convolutions on the empirical covariance matrix of signals defined over finite-dimensional Hilbert spaces, motivated by robustness and transferability properties. Yet, little is known about…

Capsule Networks (CapsNets) are able to hierarchically preserve the pose relationships between multiple objects for image classification tasks. Other than achieving high accuracy, another relevant factor in deploying CapsNets in…

Next-generation radio surveys will yield an unprecedented amount of data, warranting analysis by use of machine learning techniques. Convolutional neural networks are the deep learning technique that has proven to be the most successful in…

Vision Transformer (ViT) has emerged as a powerful architecture in the realm of modern computer vision. However, its application in certain imaging fields, such as microscopy and satellite imaging, presents unique challenges. In these…

This study develops an unsupervised learning algorithm for products of expert capsules with dynamic routing. Analogous to binary-valued neurons in Restricted Boltzmann Machines, the magnitude of a squashed capsule firing takes values…

Capsule networks (CapsNets) are an emerging trend in image processing. In contrast to a convolutional neural network, CapsNets are not vulnerable to object deformation, as the relative spatial information of the objects is preserved across…

We introduce Hyper Input Convex Neural Networks (HyCNNs), a novel neural network architecture designed for learning convex functions. HyCNNs combine the principles of Maxout networks with input convex neural networks (ICNNs) to create a…

A new spintronic nonvolatile memory cell analogous to 1T DRAM with non-destructive read is proposed. The cells can be used as neural computing units. A dual-circuit neural network architecture is proposed to leverage these devices against…

Recent advancements in computer vision have highlighted the scalability of Vision Transformers (ViTs) across various tasks, yet challenges remain in balancing adaptability, computational efficiency, and the ability to model higher-order…

Medical image segmentation has been so far achieving promising results with Convolutional Neural Networks (CNNs). However, it is arguable that in traditional CNNs, its pooling layer tends to discard important information such as positions.…

There still remains an extreme performance gap between Vision Transformers (ViTs) and Convolutional Neural Networks (CNNs) when training from scratch on small datasets, which is concluded to the lack of inductive bias. In this paper, we…

We consider the problem of jointly modeling and clustering populations of tensors by introducing a high-dimensional tensor mixture model with heterogeneous covariances. To effectively tackle the high dimensionality of tensor objects, we…

Capsule networks have gained a lot of popularity in short time due to its unique approach to model equivariant class specific properties as capsules from images. However the dynamic routing algorithm comes with a steep computational…

For the task of medical image segmentation, fully convolutional network (FCN) based architectures have been extensively used with various modifications. A rising trend in these architectures is to employ joint-learning of the target region…

Over recent years, increasingly complex approaches based on sophisticated convolutional neural network architectures have been slowly pushing performance on well-established benchmark datasets. In this paper, we take a step back to examine…

We present group equivariant capsule networks, a framework to introduce guaranteed equivariance and invariance properties to the capsule network idea. Our work can be divided into two contributions. First, we present a generic routing by…

Transformation-robustness is an important feature for machine learning models that perform image classification. Many methods aim to bestow this property to models by the use of data augmentation strategies, while more formal guarantees are…