Results 191 to 200 of about 2,754 (231)

Nonlocal Tensor-Ring Decomposition for Hyperspectral Image Denoising

IEEE Transactions on Geoscience and Remote Sensing, 2020
Hyperspectral image (HSI) denoising is a fundamental problem in remote sensing and image processing. Recently, nonlocal low-rank tensor approximation-based denoising methods have attracted much attention due to their advantage of being capable of fully exploiting the nonlocal self-similarity and global spectral correlation.
Yong Chen, Wei He, Naoto Yokoya, Ting-Zhu Huang, Xi-Le Zhao   +4 more
openaire   +1 more source

Graph-Regularized Non-Negative Tensor-Ring Decomposition for Multiway Representation Learning

IEEE Transactions on Cybernetics, 2023
Tensor-ring (TR) decomposition is a powerful tool for exploiting the low-rank property of multiway data and has been demonstrated great potential in a variety of important applications. In this article, non-negative TR (NTR) decomposition and graph-regularized NTR (GNTR) decomposition are proposed. The former equips TR decomposition with the ability to
Yuyuan Yu, Guoxu Zhou, Ning Zheng, Yuning Qiu, Shengli Xie, Qibin Zhao   +5 more
openaire   +2 more sources

Nonparametric tensor ring decomposition with scalable amortized inference

Neural Networks
Multi-dimensional data are common in many applications, such as videos and multi-variate time series. While tensor decomposition (TD) provides promising tools for analyzing such data, there still remains several limitations. First, traditional TDs assume multi-linear structures of the latent embeddings, which greatly limits their expressive power ...
Zerui Tao, Toshihisa Tanaka, Qibin Zhao
openaire   +2 more sources

An Effective Tensor Completion Method Based on Multi-linear Tensor Ring Decomposition

2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2018
By considering the balance unfolding scheme does help to catch the global information for tensor completion and the recently proposed tensor ring decomposition, in this paper a weighted multilinear tensor ring decomposition model is proposed for tensor completion and called MTRD.
Jinshi Yu, Guoxu Zhou, Qibin Zhao, Kan Xie   +3 more
openaire   +1 more source

Neural Network Compression Based on Tensor Ring Decomposition

IEEE Transactions on Neural Networks and Learning Systems
Deep neural networks (DNNs) have made great breakthroughs and seen applications in many domains. However, the incomparable accuracy of DNNs is achieved with the cost of considerable memory consumption and high computational complexity, which restricts their deployment on conventional desktops and portable devices.
Kun Xie, Can Liu, Xin Wang, Xiaocan Li, Gaogang Xie, Jigang Wen, Kenli Li   +6 more
openaire   +2 more sources

Kernel Bayesian tensor ring decomposition for multiway data recovery

Neural Networks
Tensor ring (TR) decomposition has emerged as the prevailing method for tensor completion. Earlier approaches have situated TR decomposition within a probabilistic framework, yielding satisfactory outcomes. However, these methods ignore side information or are inherently incapable of leveraging it.
Zhenhao Huang, Guoxu Zhou, Yuning Qiu, Xinqi Chen, Qibin Zhao   +4 more
openaire   +2 more sources

Hyperspectral Image Compressive Sensing Reconstruction Using Subspace-Based Nonlocal Tensor Ring Decomposition

IEEE Transactions on Image Processing, 2020
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Yong Chen, Ting-Zhu Huang, Wei He, Naoto Yokoya, Xi-Le Zhao   +4 more
openaire   +2 more sources

Tensor Ring Decomposition Guided Dictionary Learning for OCT Image Denoising

IEEE Transactions on Medical Imaging
Optical coherence tomography (OCT) is a non-invasive and effective tool for the imaging of retinal tissue. However, the heavy speckle noise, resulting from multiple scattering of the light waves, obscures important morphological structures and impairs the clinical diagnosis of ocular diseases.
Parisa Ghaderi Daneshmand, Hossein Rabbani   +1 more
openaire   +2 more sources

Decomposition of tensor spaces and block idempotents of group rings

Linear and Multilinear Algebra, 1990
Let V be a finite dimensional vector space over a field F. Let Vbe the tensor product of V with itself m times and G be a permutation group of degree n. In the case that F is the complex field, S. Pierce [6] gave a G-invariant direct decomposition of W in terms of irreducible characters of FG.
Fan Yun, Huang Qiang
openaire   +1 more source

Towards Multi-Mode Outlier Robust Tensor Ring Decomposition

Proceedings of the AAAI Conference on Artificial Intelligence
Conventional Outlier Robust Tensor Decomposition (ORTD) approaches generally represent sparse outlier corruption within a specific mode. However, such an assumption, which may hold for matrices, proves inadequate when applied to high-order tensors. In the tensor domain, the outliers are prone to be corrupted in multiple modes simultaneously. Addressing
Yuning Qiu, Guoxu Zhou, Andong Wang, Zhenhao Huang, Qibin Zhao   +4 more
openaire   +1 more source