Low-n-rank tensor recovery based on multi-linear augmented Lagrange multiplier method

Authors:
Huachun Tan;Bin Cheng;Jianshuai Feng;Guangdong Feng;Wuhong Wang;Yu-Jin Zhang
Affiliations:
Department of Transportation Engineering, Beijing Institute of Technology, Beijing 100081, PR China;Department of Transportation Engineering, Beijing Institute of Technology, Beijing 100081, PR China;Department of Transportation Engineering, Beijing Institute of Technology, Beijing 100081, PR China;Department of Transportation Engineering, Beijing Institute of Technology, Beijing 100081, PR China;Department of Transportation Engineering, Beijing Institute of Technology, Beijing 100081, PR China;Department of Electronic Engineering, Tsinghua University, Beijing 100084, PR China
Venue:
Neurocomputing
Year:
2013

Citing 10
Cited 1

Parallel and distributed computation: numerical methods

Parallel and distributed computation: numerical methods
A Model of Saliency-Based Visual Attention for Rapid Scene Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multilinear Analysis of Image Ensembles: TensorFaces

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Segmenting Foreground Objects from a Dynamic Textured Background via a Robust Kalman Filter

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Bayesian Modeling of Dynamic Scenes for Object Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fixed-Point Continuation for $\ell_1$-Minimization: Methodology and Convergence

SIAM Journal on Optimization
Tensor Decompositions and Applications

SIAM Review
A Singular Value Thresholding Algorithm for Matrix Completion

SIAM Journal on Optimization
Optimum subspace learning and error correction for tensors

ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
Image compression using the 2-D wavelet transform

IEEE Transactions on Image Processing

Tensor completion via a multi-linear low-n-rank factorization model

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

The problem of recovering data in multi-way arrays (i.e., tensors) arises in many fields such as image processing and computer vision, etc. In this paper, we present a novel method based on multi-linear n-rank and @?"0 norm optimization for recovering a low-n-rank tensor with an unknown fraction of its elements being arbitrarily corrupted. In the new method, the n-rank and @?"0 norm of the each mode of the given tensor are combined by weighted parameters as the objective function. In order to avoid relaxing the observed tensor into penalty terms, which may cause less accuracy problem, the minimization problem along each mode is accomplished by applying the augmented Lagrange multiplier method. In experiments, we test the influence of parameters on the results of the proposed method, and then compare with one state-of-the-art method on both simulated data and real data. Numerical results show that the method can reliably solve a wide range of problems at a speed at least several times faster than the state-of-the-art method while the results of the method are comparable to the previous method in terms of accuracy.