Frequency-Weighted Robust Tensor Principal Component Analysis

• URL: http://arxiv.org/abs/2004.10068v2
• Date: Tue, 10 Nov 2020 02:06:22 GMT
• Title: Frequency-Weighted Robust Tensor Principal Component Analysis
• Authors: Shenghan Wang, Yipeng Liu, Lanlan Feng, Ce Zhu
• Abstract summary: tensor singular value decomposition (t-SVD) is a popularly selected one. We incorporate frequency component analysis into t-SVD to enhance the RTPCA performance. The newly obtained frequency-weighted RTPCA can be solved by alternating direction method of multipliers.
• Score: 36.85333789033387
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Robust tensor principal component analysis (RTPCA) can separate the low-rank component and sparse component from multidimensional data, which has been used successfully in several image applications. Its performance varies with different kinds of tensor decompositions, and the tensor singular value decomposition (t-SVD) is a popularly selected one. The standard t-SVD takes the discrete Fourier transform to exploit the residual in the 3rd mode in the decomposition. When minimizing the tensor nuclear norm related to t-SVD, all the frontal slices in frequency domain are optimized equally. In this paper, we incorporate frequency component analysis into t-SVD to enhance the RTPCA performance. Specially, different frequency bands are unequally weighted with respect to the corresponding physical meanings, and the frequency-weighted tensor nuclear norm can be obtained. Accordingly we rigorously deduce the frequency-weighted tensor singular value threshold operator, and apply it for low rank approximation subproblem in RTPCA. The newly obtained frequency-weighted RTPCA can be solved by alternating direction method of multipliers, and it is the first time that frequency analysis is taken in tensor principal component analysis. Numerical experiments on synthetic 3D data, color image denoising and background modeling verify that the proposed method outperforms the state-of-the-art algorithms both in accuracy and computational complexity.

Related papers

• Localized Sparse Principal Component Analysis of Multivariate Time Series in Frequency Domain [0.0]
  We introduce a formulation and consistent estimation procedure for interpretable principal component analysis for high-dimensional time series in the frequency domain. An efficient frequency-sequential algorithm is developed to compute sparse-localized estimates of the low-dimensional principal subspaces of the signal process.
  arXiv  Detail & Related papers  (2024-08-15T14:30:34Z)
• Low-Multi-Rank High-Order Bayesian Robust Tensor Factorization [7.538654977500241]
  We propose a novel high-order TRPCA method, named as Low-Multi-rank High-order Robust Factorization (LMH-BRTF) within the Bayesian framework. Specifically, we decompose the observed corrupted tensor into three parts, i.e., the low-rank component, the sparse component, and the noise component. By constructing a low-rank model for the low-rank component based on the order-$d$ t-SVD, LMH-BRTF can automatically determine the tensor multi-rank.
  arXiv  Detail & Related papers  (2023-11-10T06:15:38Z)
• One-Dimensional Deep Image Prior for Curve Fitting of S-Parameters from Electromagnetic Solvers [57.441926088870325]
  Deep Image Prior (DIP) is a technique that optimized the weights of a randomly-d convolutional neural network to fit a signal from noisy or under-determined measurements. Relative to publicly available implementations of Vector Fitting (VF), our method shows superior performance on nearly all test examples.
  arXiv  Detail & Related papers  (2023-06-06T20:28:37Z)
• Transform Once: Efficient Operator Learning in Frequency Domain [69.74509540521397]
  We study deep neural networks designed to harness the structure in frequency domain for efficient learning of long-range correlations in space or time. This work introduces a blueprint for frequency domain learning through a single transform: transform once (T1)
  arXiv  Detail & Related papers  (2022-11-26T01:56:05Z)
• DeepTensor: Low-Rank Tensor Decomposition with Deep Network Priors [45.183204988990916]
  DeepTensor is a framework for low-rank decomposition of matrices and tensors using deep generative networks. We explore a range of real-world applications, including hyperspectral image denoising, 3D MRI tomography, and image classification.
  arXiv  Detail & Related papers  (2022-04-07T01:09:58Z)
• Semi-tensor Product-based TensorDecomposition for Neural Network Compression [57.95644775091316]
  This paper generalizes classical matrix product-based mode product to semi-tensor mode product. As it permits the connection of two factors with different dimensionality, more flexible and compact tensor decompositions can be obtained.
  arXiv  Detail & Related papers  (2021-09-30T15:18:14Z)
• Regularization by Denoising Sub-sampled Newton Method for Spectral CT Multi-Material Decomposition [78.37855832568569]
  We propose to solve a model-based maximum-a-posterior problem to reconstruct multi-materials images with application to spectral CT. In particular, we propose to solve a regularized optimization problem based on a plug-in image-denoising function. We show numerical and experimental results for spectral CT materials decomposition.
  arXiv  Detail & Related papers  (2021-03-25T15:20:10Z)
• Fourth-Order Nonlocal Tensor Decomposition Model for Spectral Computed Tomography [20.03088101097943]
  Spectral computed tomography (CT) can reconstruct spectral images from different energy bins using photon counting detectors (PCDs) Due to the limited photons and counting rate in the corresponding spectral fraction, the reconstructed spectral images usually suffer from severe noise. In this paper, a fourth-order nonlocal tensor decomposition model for spectral CT image reconstruction (FONT-SIR) is proposed.
  arXiv  Detail & Related papers  (2020-10-27T15:14:36Z)
• Robust Tensor Principal Component Analysis: Exact Recovery via Deterministic Model [5.414544833902815]
  This paper proposes a new method to analyze Robust tensor principal component analysis (RTPCA) It is based on the recently developed tensor-tensor product and tensor singular value decomposition (t-SVD)
  arXiv  Detail & Related papers  (2020-08-05T16:26:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.