Related papers: VPNet: Variable Projection Networks
Transformers have revolutionized computer vision and natural language processing, but their high computational complexity limits their application in high-resolution image processing and long-context analysis. This paper introduces…
Heterogeneous Graph Neural Networks (HGNNs) have exhibited powerful performance in heterogeneous graph learning by aggregating information from various types of nodes and edges. However, existing heterogeneous graph models often struggle to…
Convolutional neural networks (CNNs), in a few decades, have outperformed the existing state of the art methods in classification context. However, in the way they were formalised, CNNs are bound to operate on euclidean spaces. Indeed,…
The importance of inference in Machine Learning (ML) has led to an explosive number of different proposals in ML, and particularly in Deep Learning. In an attempt to reduce the complexity of Convolutional Neural Networks, we propose a…
Artificial neural networks (ANNs) based machine learning models and especially deep learning models have been widely applied in computer vision, signal processing, wireless communications, and many other domains, where complex numbers occur…
Visual-frame prediction is a pixel-dense prediction task that infers future frames from past frames. Lacking of appearance details, low prediction accuracy and high computational overhead are still major problems with current models or…
Prototypical part neural networks (ProtoPartNNs), namely PROTOPNET and its derivatives, are an intrinsically interpretable approach to machine learning. Their prototype learning scheme enables intuitive explanations of the form, this…
Network virtualization is an important concept to overcome the ossification of today's Internet as it facilitates innovation also in the network core and as it promises a more efficient use of the given resources and infrastructure. Virtual…
Predictive monitoring of business processes is a subfield of process mining that aims to predict, among other things, the characteristics of the next event or the sequence of next events. Although multiple approaches based on deep learning…
Complex-valued Neural Networks (CVNNs) are often motivated by domains where information is naturally encoded in magnitude and phase. Yet complex-valued inputs alone do not determine when complex arithmetic improves learning: the label…
In the last decade, convolutional neural networks (ConvNets) have dominated and achieved state-of-the-art performances in a variety of medical imaging applications. However, the performances of ConvNets are still limited by lacking the…
Deep Convolutional Neural Network (CNN) is a special type of Neural Networks, which has shown exemplary performance on several competitions related to Computer Vision and Image Processing. Some of the exciting application areas of CNN…
3D object detection is receiving increasing attention from both industry and academia thanks to its wide applications in various fields. In this paper, we propose Point-Voxel Region-based Convolution Neural Networks (PV-RCNNs) for 3D object…
Investigating relationships between variables in multi-dimensional data sets is a common task for data analysts and engineers. More specifically, it is often valuable to understand which ranges of which input variables lead to particular…
Convolutional neural networks have recently shown excellent results in general object detection and many other tasks. Albeit very effective, they involve many user-defined design choices. In this paper we want to better understand these…
We introduce the value iteration network (VIN): a fully differentiable neural network with a `planning module' embedded within. VINs can learn to plan, and are suitable for predicting outcomes that involve planning-based reasoning, such as…
To improve the discriminative and generalization ability of lightweight network for face recognition, we propose an efficient variable group convolutional network called VarGFaceNet. Variable group convolution is introduced by VarGNet to…
The usage of 3D vision algorithms, such as shape reconstruction, remains limited because they require inputs to be at a fixed canonical rotation. Recently, a simple equivariant network, Vector Neuron (VN) has been proposed that can be…
The integration of deep learning based systems in clinical practice is often impeded by challenges rooted in limited and heterogeneous medical datasets. In addition, the field has increasingly prioritized marginal performance gains on a…
Unsupervised video object learning seeks to decompose video scenes into structural object representations without any supervision from depth, optical flow, or segmentation. We present VONet, an innovative approach that is inspired by MONet.…