mlsanityData to 7 Oct 2026

Coarse to Fine Two-Stage Approach to Robust Tensor Completion of Visual Data

arXiv 2106.10422 ↗First posted 19 Jun 2021cs.LG stat.MLcited by 3

Not on the map. Why?

Abstract (arXiv)

Tensor completion is the problem of estimating the missing values of high-order data from partially observed entries. Data corruption due to prevailing outliers poses major challenges to traditional tensor completion algorithms, which catalyzed the development of robust algorithms that alleviate the effect of outliers. However, existing robust methods largely presume that the corruption is sparse, which may not hold in practice. In this paper, we develop a two-stage robust tensor completion approach to deal with tensor completion of visual data with a large amount of gross corruption. A novel coarse-to-fine framework is proposed which uses a global coarse completion result to guide a local patch refinement process. To efficiently mitigate the effect of a large number of outliers on tensor recovery, we develop a new M-estimator-based robust tensor ring recovery method which can adaptively identify the outliers and alleviate their negative effect in the optimization. The experimental results demonstrate the superior performance of the proposed approach over state-of-the-art robust algorithms for tensor completion.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 20 of its 77 references that are in the map. First posted on arXiv 19 Jun 2021.

Builds on

20 of 77 references.

References · 20

  1. 2016Tensor Ring Decompositioncited by 125
  2. 2017Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answeringcited by 117
  3. 2015Exact tensor completion using t-SVDcited by 70
  4. 2016Efficient tensor completion for color image and video recovery: Low-rank tensor traincited by 61
  5. 2017Tensor Completion Algorithms in Big Data Analyticscited by 48
  6. 2017Efficient Low Rank Tensor Ring Completioncited by 45
  7. 2018Tensor Ring Decomposition with Rank Minimization on Latent Space: An Efficient Approach for Tensor Completioncited by 42
  8. 2018Robust Graph Learning from Noisy Datacited by 34
  9. 2013Robust Low-rank Tensor Recovery: Models and Algorithmscited by 33
  10. 2016Low-tubal-rank Tensor Completion using Alternating Minimizationcited by 18
  11. 2019Tensor-Ring Nuclear Norm Minimization and Application for Visual Data Completioncited by 12
  12. 2014On the Convergence of Alternating Direction Lagrangian Methods for Nonconvex Structured Optimization Problemscited by 8
8 more
  1. 2019Provable Tensor Ring Completioncited by 8
  2. 2016Top-N Recommender System via Matrix Completioncited by 7
  3. 2018Exactly Robust Kernel Principal Component Analysiscited by 7
  4. 2020Tensor train rank minimization with nonlocal self-similarity for tensor completioncited by 5
  5. 2020Robust Non-Linear Matrix Factorization for Dictionary Learning, Denoising, and Clusteringcited by 5
  6. 2017High-order Tensor Completion for Data Recovery via Sparse Tensor-train Optimizationcited by 3
  7. 2015An Iterative Reweighted Method for Tucker Decomposition of Incomplete Multiway Tensorscited by 1
  8. 2015Restricted Low-Rank Approximation via ADMMcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 0; 2025: 1.

3 papers.

  1. 2023Nonconvex Robust High-Order Tensor Completion Using Randomized Low-Rank Approximationcited by 7
  2. 2023Robust Low-Rank Matrix Completion via a New Sparsity-Inducing Regularizercited by 0
  3. 2025Tensor Completion via Monotone Inclusion: Generalized Low-Rank Priors Meet Deep Denoiserscited by 0