Skip to main content
SpringerLink
Log in

Sparse and Truncated Nuclear Norm Based Tensor Completion

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

One of the main difficulties in tensor completion is the calculation of the tensor rank. Recently a tensor nuclear norm, which is equal to the weighted sum of matrix nuclear norms of all unfoldings of the tensor, was proposed to address this issue. However, in this approach, all the singular values are minimized simultaneously. Hence the tensor rank may not be well approximated. In addition, many existing algorithms ignore the structural information of the tensor. This paper presents a tensor completion algorithm based on the proposed tensor truncated nuclear norm, which is superior to the traditional tensor nuclear norm. Furthermore, to maintain the structural information, a sparse regularization term, defined in the transform domain, is added into the objective function. Experimental results showed that our proposed algorithm outperforms several state-of-the-art tensor completion schemes.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Kim E, Lee M, Choi C-H, Kwak N, Oh Songhwai (2015) Efficient L1-norm-based low-rank matrix approximations for large-scale problems using alternating rectified gradient method. IEEE Trans Neural Netw Learn Syst 26(2):237–251

    Article  MathSciNet  Google Scholar 

  2. Li L, Li S, Fu Y (2013) Discriminative dictionary learning with low-rank regularization for face recognition. In: Proceedings of 10th IEEE international conference and workshops on automatic face and gesture recognition (FG), 2013, pp 1–6

  3. Ma R, Barzigar N, Roozgard A, Cheng S (2014) Decomposition approach for low-rank matrix completion and its applications. IEEE Trans Signal Process 62(7):1671–1683

    Article  MathSciNet  Google Scholar 

  4. Liu G, Lin Z, Yan S, Sun J, Yu Y, Ma Y (2013a) Robust recovery of subspace structures by low-rank representation. IEEE Trans Pattern Anal Mach Intell 35(1):171–184

    Article  Google Scholar 

  5. Coupier David, Desolneux Agnes, Ycart Bernard (2005) Image denoising by statistical area thresholding. J Math Imaging Vis 22(2–3):183–197

    Article  MathSciNet  Google Scholar 

  6. Tessens L, Pizurica A, Alecu A, Munteanu A, Philips W (2008) Context adaptive image denoising through modeling of curvelet domain statistics. J Electron Imaging 17(3):03021:1–03021:17

    Article  Google Scholar 

  7. Efros A, Leung T (1999) Texture synthesis by non-parametric sampling. In: Proceedings of 7th international conference on computer vision 1999, pp 1033–1038

  8. Liu J, Musialski P, Wonka P, Ye J (2013b) Tensor completion for estimating missing values in visual data. IEEE Trans Pattern Anal Mach Intell 35(1):208–220

    Article  Google Scholar 

  9. Candès E, Recht B (2009) Exact matrix completion via convex optimization. Found Comput Math 9(6):717–772

    Article  MathSciNet  MATH  Google Scholar 

  10. Okatani T, Yoshida T, Deguchi K (2011) Efficient algorithm for low-rank matrix factorization with missing components and performance comparison of latest algorithms. In: Proceedings IEEE international conference computer vision, pp 842–849

  11. Zhang Z, Ganesh A, Liang X, Ma Y (2012) Tilt: transform invariant low-rank textures. Int J Comput Vis 99(1):1–24

    Article  MathSciNet  MATH  Google Scholar 

  12. Ji H, Liu C, Shen Z, Xu Y (2010) Robust video denoising using low rank matrix completion. In: Proceedings of IEEE international conference computer vision and pattern recognition 2010, pp 1791–1798

  13. Candès EJ, Tao T (2010) The power of convex relaxation: near-optimal matrix completion. IEEE Trans Inf Theory 56(5):2053–2080

    Article  MathSciNet  Google Scholar 

  14. Cai J-F, Candès EJ, Shen Z (2010) A singular value thresholding algorithm for matrix completion. SIAM J Optim 20(4):1956–1982

    Article  MathSciNet  MATH  Google Scholar 

  15. Ma S, Goldfarb D, Chen L (2011) Fixed point and bregman iterative methods for matrix rank minimization. Math. Program. 128(1–2):321–353

    Article  MathSciNet  MATH  Google Scholar 

  16. Hu Y, Zhang D, Ye J, Li X, He X (2013) Fast and accurate matrix completion via truncated nuclear norm regularization. IEEE Trans Pattern Anal Mach Intell 35(9):2117–2130

    Article  Google Scholar 

  17. Xu Y, Hao R, Yin W, Su Z (2015) Parallel matrix factorization for low-rank tensor completion. Inverse Problems and Imaging 9(2):601–624

    Article  MathSciNet  MATH  Google Scholar 

  18. Kolda TG, Bader BW (2009) Tensor decompositions and applications. SIAM Rev 51(3):455–500

    Article  MathSciNet  MATH  Google Scholar 

  19. Yang L, Huang Z-H, Shi X (2013) A fixed point iterative method for low n-rank tensor pursuit. IEEE Trans Signal Process 61(11):2952–2962

    Article  MathSciNet  Google Scholar 

  20. Boyd S, Parikh N, Chu E, Peleato B, Eckstein J (2011) Distributed optimization and statistical learning via the alternating direction method of multipliers. Found Trends Mach Learn 3(1):1–122

    Article  MATH  Google Scholar 

  21. Rauhut H, Ward R (2016) Interpolation via weighted l1 minimization. Appl Comput Harmonic Anal 40(2):321–351

  22. Taheri S, Qiu Q, Chellappa R (2014) Structure-preserving sparse decomposition for facial expression analysis. IEEE Trans Image Process 23(8):3590–3603

    Article  MathSciNet  Google Scholar 

  23. Merhav N, Kresch R (1998) Approximate convolution using DCT coefficient multipliers. IEEE Trans Circuits Syst Video Technol 8(4):378–385

    Article  Google Scholar 

  24. Donoho DL, Johnstone IM (1995) Adapting to unknown smoothness via wavelet shrinkage. J Am Stat Assoc 90:1200–1224

    Article  MathSciNet  MATH  Google Scholar 

  25. Liang X, Ren X, Zhang Z, Ma Y (2012) Repairing sparse low-rank texture. In: Proceedings of European conference computer vision, pp 482–495

Download references

Acknowledgments

The work was supported by a research grant from the Hong Kong SAR Government (CityU 116511).

Author information

Authors and Affiliations

  1. Department of Electronic Engineering, City University of Hong Kong, Hong Kong, China

    Zi-Fa Han, Chi-Sing Leung, Long-Ting Huang & Hing Cheung So

Authors
  1. Zi-Fa Han
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chi-Sing Leung
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Long-Ting Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hing Cheung So
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Chi-Sing Leung.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Han, ZF., Leung, CS., Huang, LT. et al. Sparse and Truncated Nuclear Norm Based Tensor Completion. Neural Process Lett 45, 729–743 (2017). https://doi.org/10.1007/s11063-016-9503-4

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-016-9503-4

Keywords

Search

Navigation