English

Fully-Connected Tensor Network Decomposition for Robust Tensor Completion Problem

Computer Vision and Pattern Recognition 2021-10-19 v1

Abstract

The robust tensor completion (RTC) problem, which aims to reconstruct a low-rank tensor from partially observed tensor contaminated by a sparse tensor, has received increasing attention. In this paper, by leveraging the superior expression of the fully-connected tensor network (FCTN) decomposition, we propose a FCTN\textbf{FCTN}-based r\textbf{r}obust c\textbf{c}onvex optimization model (RC-FCTN) for the RTC problem. Then, we rigorously establish the exact recovery guarantee for the RC-FCTN. For solving the constrained optimization model RC-FCTN, we develop an alternating direction method of multipliers (ADMM)-based algorithm, which enjoys the global convergence guarantee. Moreover, we suggest a FCTN\textbf{FCTN}-based r\textbf{r}obust n\textbf{n}onc\textbf{c}onvex optimization model (RNC-FCTN) for the RTC problem. A proximal alternating minimization (PAM)-based algorithm is developed to solve the proposed RNC-FCTN. Meanwhile, we theoretically derive the convergence of the PAM-based algorithm. Comprehensive numerical experiments in several applications, such as video completion and video background subtraction, demonstrate that proposed methods are superior to several state-of-the-art methods.

Keywords

Cite

@article{arxiv.2110.08754,
  title  = {Fully-Connected Tensor Network Decomposition for Robust Tensor Completion Problem},
  author = {Yun-Yang Liu and Xi-Le Zhao and Guang-Jing Song and Yu-Bang Zheng and Ting-Zhu Huang},
  journal= {arXiv preprint arXiv:2110.08754},
  year   = {2021}
}