Related papers: An Adaptive Orthogonal Convolution Scheme for Effi…
We consider the problem of minimizing a non-convex function over a smooth manifold $\mathcal{M}$. We propose a novel algorithm, the Orthogonal Directions Constrained Gradient Method (ODCGM) which only requires computing a projection onto a…
Heterogeneous graph neural networks aim to discover discriminative node embeddings and relations from multi-relational networks.One challenge of heterogeneous graph learning is the design of learnable meta-paths, which significantly…
Motivation Modern molecular sequence analysis increasingly relies on automated and robust software tools for interpretation, annotation, and biological insight. The Analysis of Orthologous Collections (AOC) application automates the…
Traffic prediction is a critical component of intelligent transportation systems, enabling applications such as congestion mitigation and accident risk prediction. While recent research has explored both graph-based and grid-based…
Nowadays, service robots are appearing more and more in our daily life. For this type of robot, open-ended object category learning and recognition is necessary since no matter how extensive the training data used for batch learning, the…
Emerging AI applications such as ChatGPT, graph convolutional networks, and other deep neural networks require massive computational resources for training and inference. Contemporary computing platforms such as CPUs, GPUs, and TPUs are…
Medical image segmentation plays a vital role in various clinical applications, enabling accurate delineation and analysis of anatomical structures or pathological regions. Traditional CNNs have achieved remarkable success in this field.…
Spectral graph convolutional neural networks (CNNs) require approximation to the convolution to alleviate the computational complexity, resulting in performance loss. This paper proposes the topology adaptive graph convolutional network…
Benefiting from the great success of deep learning in computer vision, CNN-based object detection methods have drawn significant attentions. Various frameworks have been proposed which show awesome and robust performance for a large range…
Training convolutional neural networks with a Lipschitz constraint under the $l_{2}$ norm is useful for provable adversarial robustness, interpretable gradients, stable training, etc. While 1-Lipschitz networks can be designed by imposing a…
The booming of 3D recognition in the 2020s began with the introduction of point cloud transformers. They quickly overwhelmed sparse CNNs and became state-of-the-art models, especially in 3D semantic segmentation. However, sparse CNNs are…
Despite several algorithmic advances in the training of convolutional neural networks (CNNs) over the years, their generalization capabilities are still subpar across several pertinent domains, particularly within open-set tasks often found…
Orthogonal Gradient Descent (OGD) has emerged as a powerful method for continual learning. However, its Euclidean projections do not leverage the underlying information-geometric structure of the problem, which can lead to suboptimal…
While state-of-the-art development in CNN topology, such as VGGNet and ResNet, have become increasingly accurate, these networks are computationally expensive involving billions of arithmetic operations and parameters. To improve the…
It is a highly desirable property for deep networks to be robust against small input changes. One popular way to achieve this property is by designing networks with a small Lipschitz constant. In this work, we propose a new technique for…
Recognizing the substantial computational cost of backpropagation (BP), non-BP methods have emerged as attractive alternatives for efficient learning on emerging neuromorphic systems. However, existing non-BP approaches still face critical…
Gaussian Process (GP) models are a class of flexible non-parametric models that have rich representational power. By using a Gaussian process with additive structure, complex responses can be modelled whilst retaining interpretability.…
This paper introduces AdaptoVision, a novel convolutional neural network (CNN) architecture designed to efficiently balance computational complexity and classification accuracy. By leveraging enhanced residual units, depth-wise separable…
The convolutional neural network (CNN) is one of the most commonly used architectures for computer vision tasks. The key building block of a CNN is the convolutional kernel that aggregates information from the pixel neighborhood and shares…
This paper proposes a novel heterogeneous grid convolution that builds a graph-based image representation by exploiting heterogeneity in the image content, enabling adaptive, efficient, and controllable computations in a convolutional…