Results 241 to 250 of about 1,077,071 (292)

An Accuracy-Preserving Neural Network Compression via Tucker Decomposition

IEEE Transactions on Sustainable Computing
Deep learning has made remarkable progress across many domains, enabled by the capabilities of over-parameterized neural networks with increasing complexity.
Can Liu, Kun Xie, Jigang Wen, Gaogang Xie, Kenli Li   +4 more
semanticscholar   +1 more source

LSPTD: Low-Rank and Spatiotemporal Priors Enhanced Tucker Decomposition for Internet Traffic Data Imputation

2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), 2023
Low-rank tensor methods and their relaxation forms have performed excellently in tensor completion problems, including internet traffic data imputation. However, most are based on the unfolding matrix's nuclear norm, which inevitably destroys the traffic
W. Gong, Zhejun Huang, Lili Yang
semanticscholar   +1 more source

Nonnegative Tucker decomposition with alpha-divergence

2008 IEEE International Conference on Acoustics, Speech and Signal Processing, 2008
Nonnegative tucker decomposition (NTD) is a recent multiway extension of nonnegative matrix factorization (NMF), where nonnega- tivity constraints are incorporated into Tucker model. In this paper we consider alpha-divergence as a discrepancy measure and derive multiplicative updating algorithms for NTD.
Yong-Deok Kim, Andrzej Cichocki, Seungjin Choi   +2 more
openaire   +1 more source

Image inpainting via Smooth Tucker decomposition and Low-rank Hankel constraint

International Journal of Computer Applications, 2023
Image inpainting, aiming at exactly recovering missing pixels from partially observed entries, is typically an ill-posed problem. As a powerful constraint, low-rank priors have been widely applied in image inpainting to transform such problems into well ...
Jing Cai, Jiawei Jiang, Yibin Wang, Jian Zheng, Honghui Xu   +4 more
semanticscholar   +1 more source

Wafer Pattern Recognition Using Tucker Decomposition

2019 IEEE 37th VLSI Test Symposium (VTS), 2019
In production test data analytics, it is often that an analysis involves the recognition of a conceptual pattern on a wafer map. A wafer pattern may hint a particular issue in the production by itself or guide the analysis into a certain direction. In this work, we introduce a novel approach to recognize patterns on a wafer map of pass/fail locations ...
Ahmed Wahba, Li-C. Wang, Zheng Zhang, Nik Sumikawa   +3 more
openaire   +1 more source

Stacked Tucker Decomposition With Multi-Nonlinear Products for Remote Sensing Imagery Inpainting

IEEE Transactions on Geoscience and Remote Sensing
In the field of remote sensing (RS) imaging, the occurrence of adverse meteorological conditions or sensor malfunctions can lead to missing data, posing a substantial impediment.
Shuang Xu, Jiangjun Peng, Teng-Yu Ji, Xiangyong Cao, Kai Sun, Rongrong Fei, Deyu Meng   +6 more
semanticscholar   +1 more source

Three-Order Tensor Creation and Tucker Decomposition for Infrared Small-Target Detection

IEEE Transactions on Geoscience and Remote Sensing, 2021
Existing infrared small-target detection methods tend to perform unsatisfactorily when encountering complex scenes, mainly due to the following: 1) the infrared image itself has a low signal-to-noise ratio (SNR) and insufficient detailed/texture ...
Mingjing Zhao, Wei Li, Lu Li, Pengge Ma, Zhaoquan Cai, R. Tao   +5 more
semanticscholar   +1 more source

Unsupervised Hyperspectral and Multispectral Image Blind Fusion Based on Deep Tucker Decomposition Network With Spatial–Spectral Manifold Learning

IEEE Transactions on Neural Networks and Learning Systems
Hyperspectral image (HSI) and multispectral image (MSI) fusion aims to generate high spectral and spatial resolution hyperspectral image (HR-HSI) by fusing high-resolution multispectral image (HR-MSI) and low-resolution hyperspectral image (LR-HSI ...
He Wang, Yang Xu, Zebin Wu, Zhihui Wei
semanticscholar   +1 more source

Parallel Tucker Decomposition with Numerically Accurate SVD

50th International Conference on Parallel Processing, 2021
Tucker decomposition is a low-rank tensor approximation that generalizes a truncated matrix singular value decomposition (SVD). Existing parallel software has shown that Tucker decomposition is particularly effective at compressing terabyte-sized multidimensional scientific simulation datasets, computing reduced representations that satisfy a specified
Zitong Li, Qiming Fang, Grey Ballard
openaire   +1 more source

Double‐Tucker Decomposition and Its Computations

Numerical Linear Algebra with Applications
ABSTRACTThe famous Tucker decomposition has been widely and successfully used in many fields. However, it often suffers from the curse of dimensionality due to the core tensor and large ranks. To tackle this issue, we introduce an additional core tensor into Tucker decomposition and propose the so‐called double‐Tucker (dTucker) decomposition.
Mengyu Wang, Honghua Cui, Hanyu Li
openaire   +1 more source