Saliency Detection via Diversity-Induced Multi-view Matrix Decomposition

  • Xiaoli SunEmail author
  • Zhixiang He
  • Xiujun Zhang
  • Wenbin Zou
  • George Baciu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10111)


In this paper, a diversity-induced multi-view matrix decomposition model (DMMD) for salient object detection is proposed. In order to make the background cleaner, \(\mathrm {Schatten}\)-p norm with an appropriate value of p in (0,1] is used to constrain the background part. A group sparsity induced norm is imposed on the foreground (salient part) to describe potential spatial relationships of patches. And most importantly, a diversity-induced multi-view regularization based Hilbert-Schmidt Independence Criterion (HSIC), is employed to explore the complementary information of different features. The independence between the multiple features will be enhanced. The optimization problem can be solved through an augmented Lagrange multipliers method. Finally, high-level priors are merged to boom the salient regions detection. Experiments on the widely used MSRA-5000 dataset show that the DMMD model outperforms other state-of-the-art methods.


Salient Object Salient Region Saliency Detection Nuclear Norm Salient Object Detection 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



This work is supported in part by the National Natural Science Funds of China (Grant Nos. 61472257, 61402290, 61401287) and in part by the Natural Science Foundation of Shenzhen under Grant JCYJ 20160307154003475 and 2016050617251253.


  1. 1.
    Zuo, W., Meng, D., Zhang, L., Feng, X., Zhang, D.: A generalized iterated shrinkage algorithm for non-convex sparse coding. In: ICCV, pp. 217–224 (2013)Google Scholar
  2. 2.
    Yan, Q., Xu, L., Shi, J., Jia, J.: Hierarchical saliency detection. In: CVPR, pp. 1155–1162 (2013)Google Scholar
  3. 3.
    Yang, C., Zhang, L., Lu, H., Ruan, X., Yang, M.: Saliency detection via graph-based manifold ranking. In: CVPR, pp. 3166–3173 (2013)Google Scholar
  4. 4.
    Perazzi, F., Krähenbühl, P., Pritch, Y., Hornung, A.: Saliency filters: Contrast based filtering for salient region detection. In: CVPR, pp. 733–740 (2012)Google Scholar
  5. 5.
    Jiang, H., Wang, J., Yuan, Z., Liu, T., Zheng, N., Li, S.: Automatic salient object segmentation based on context and shape prior. In: BMVC (2011)Google Scholar
  6. 6.
    Shen, X., Wu, Y.: A unified approach to salient object detection via low rank matrix recovery. In: CVPR, pp. 853–860 (2012)Google Scholar
  7. 7.
    Cheng, M.-M., Zhang, G., Mitra, N.J., Huang, X., Hu, S.-M.: Global contrast based salient region detection. In: CVPR, pp. 409–416 (2011)Google Scholar
  8. 8.
    Chang, K.-Y., Liu, T.-L., Chen, H.-T., Lai, S.-H.: Fusing generic objectness and visual saliency for salient object detection. In: ICCV, pp. 914–921 (2011)Google Scholar
  9. 9.
    Zhu, W., Liang, S., Wei, Y., Sun, J.: Saliency optimization from robust background detection. In: CVPR, pp. 2814–2821 (2014)Google Scholar
  10. 10.
    Liu, G., Lin, Z., Yu, Y.: Robust subspace segmentation by low-rank representation. In: ICML, pp. 663–670 (2010)Google Scholar
  11. 11.
    Lang, C., Liu, G., Yu, J., Yan, S.: Saliency detection by multitask sparsity pursuit. IEEE Trans. Image Process. 21, 1327–1338 (2012)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Zou, W., Kpalma, K., Liu, Z., Ronsin, J.: Segmentation driven low-rank matrix recovery for saliency detection. In: BMVC (2013)Google Scholar
  13. 13.
    Candès, E., Li, X., Ma, Y., Wright, J.: Robust principal component analysis? J. ACM 58, 11–20 (2011)MathSciNetCrossRefzbMATHGoogle Scholar
  14. 14.
    Lin, Z., Chen, M.-M., Ma, Y.: The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices. arXiv preprint arxiv:1009.5055 (2010)
  15. 15.
    Peng, H., Li, B., Ji, R., Hu, W., Xiong, W., Lang, C.: Salient object detection via low-rank and structured sparse matrix decomposition. In: AAAI, pp. 796–802 (2013)Google Scholar
  16. 16.
    Simoncelli, E., Freeman, W.: The steerable pyramid: A flexible architecture for multi-scale derivative computation. In: ICIP (1995)Google Scholar
  17. 17.
    Feichtinger, H.G., Strohmer, T.: Gabor Analysis and Algorithms: Theory and Applications. Birkhäuser, Basel (2012)zbMATHGoogle Scholar
  18. 18.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Susstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 12, 2274–2282 (2012)CrossRefGoogle Scholar
  19. 19.
    Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59, 167–181 (2004)CrossRefGoogle Scholar
  20. 20.
    Cetin, M., Karl, W.C.: Feature-enhanced synthetic aperture radar image formation based on nonquadratic regularization. IEEE Trans. Image Process. 10, 623–631 (2001)CrossRefzbMATHGoogle Scholar
  21. 21.
    Chartrand, R.: Exact reconstruction of sparse signals via nonconvex minimization. IEEE Sig. Process. Lett. 14, 707–710 (2007)CrossRefGoogle Scholar
  22. 22.
    Chartrand, R., Staneva, V.: Restricted isometry properties and nonconvex compressive sensing. Inverse Prob. 24, 657–682 (2008)MathSciNetCrossRefzbMATHGoogle Scholar
  23. 23.
    Cao, X., Zhang, C., Fu, H., Liu, S., Zhang, H.: Diversity-induced multi-view subspace clustering. In: CVPR, pp. 586–594 (2015)Google Scholar
  24. 24.
    Peng, H., Li, B., Ling, H., Hu, W., Xiong, W., Maybank, S.J.: Salient object detection via structured matrix decomposition. IEEE Trans. Pattern Anal. Mach. Intell. (2016). In PressGoogle Scholar
  25. 25.
    Chaudhuri, K., Kakade, S.M., Livescu, K., Sridharan, K.: Multi-view clustering via canonical correlation analysis. In: ICML, pp. 129–136 (2009)Google Scholar
  26. 26.
    Tang, W., Lu, Z., Dhillon, I.S.: Clustering with multiple graphs. In: ICDM, pp. 1016–1021 (2009)Google Scholar
  27. 27.
    Cai, D., He, X., Han, J., Huang, T.S.: Graph regularized nonnegative matrix factorization for data representation. IEEE Trans. Pattern Anal. Mach. Intell. 33, 1548–1560 (2011)CrossRefGoogle Scholar
  28. 28.
    Tong, N., Lu, H., Ruan, X., Yang, M.-H.: Salient object detection via bootstrap learning. In: CVPR, pp. 1884–1892 (2015)Google Scholar
  29. 29.
    Li, X., Lu, H., Zhang, L., Ruan, X., Yang, M.-H.: Saliency detection via dense and sparse reconstruction. In: ICCV, pp. 2976–2983 (2013)Google Scholar
  30. 30.
    Zhang, X., Sun, X., Xu, C., Baciu, G.: Multiple feature distinctions based saliency flow model. Pattern Recogn. 54, 190–205 (2016)CrossRefGoogle Scholar
  31. 31.
    Zhang, X., Xu, C., Sun, X., Baciu, G.: Schatten-q regularizer constrained low rank subspace clustering model. Neurocomputing 182, 36–47 (2016)CrossRefGoogle Scholar
  32. 32.
    He, Z., Sun, X., Zhang, X., Xu, C.: Saliency detection via nonconvex regularization based matrix decomposition. In: International Conference on Computational Intelligence and Security, pp. 243–247 (2015)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Xiaoli Sun
    • 1
    Email author
  • Zhixiang He
    • 1
  • Xiujun Zhang
    • 2
  • Wenbin Zou
    • 3
  • George Baciu
    • 4
  1. 1.College of Mathematics and StatisticsShenzhen UniversityShenzhenChina
  2. 2.School of Electronic and Communication EngineeringShenzhen PolytechnicShenzhenChina
  3. 3.College of Information EngineeringShenzhen UniversityShenzhenChina
  4. 4.Department of ComputingThe Hong Kong Polytechnic UniversityHung HomHong Kong

Personalised recommendations