Multimedia Tools and Applications

, Volume 77, Issue 3, pp 3317–3337 | Cite as

Salient object detection via robust dictionary representation

  • Huaxin Xiao
  • Weiya Ren
  • Wei Wang
  • Yu Liu
  • Maojun Zhang


The theory of sparse and low-rank representation has worked competitive performance in the field of salient object detection. Generally, the salient object is represented as sparse error while the non-salient region is constrained by the property of low-rank. However, sparsity ignores the global structure which may break up the low-rank property. Besides, the outliers always lead to a poor representation. To handle these problems, this paper proposes a robust representation based on a discriminative dictionary which consists of non-salient and salient templates. Three weight measures are introduced and combined to select the proper templates. The coefficients on dictionary are restricted by 2,1-norm. Correspondingly, Frobenius norm instead of 1-norm is exploited to constrain the distribution of representation error. We compare the proposed algorithm against 17 state-of-the-art methods on 4 popular datasets by 6 evaluation metrics and demonstrate the competitive performance in terms of qualitative and quantitative results.


Salient object detection Low-rank representation Sparse representation Matrix decomposition 



This research was partially supported by National Natural Science Foundation of China under project No. 61403403, No. 71673293 and China Postdoctoral Science Foundation under project No. 2015M52707.


  1. 1.
    Achanta R, Hemami S, Süsstrunk S (2009) Frequency-tuned salient region detection. In: Proc. IEEE CVPR, pp 1597–1604Google Scholar
  2. 2.
    Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Süsstrunk S (2012) Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34(11):2274–2281CrossRefGoogle Scholar
  3. 3.
    Alexe B, Deselaers T, Ferrari V (2012) Measuring the objectness of image windows. IEEE Trans Pattern Anal Mach Intell 34(11):2189–2202CrossRefGoogle Scholar
  4. 4.
    Borji A, Itti L (2012) Exploiting local and global patch rarities for saliency detection. In: Proc IEEE CVPR, pp 478–485Google Scholar
  5. 5.
    Borji A, Cheng M M, Jiang H, Li J (2015) Salient object detection: a benchmark. IEEE Trans Image Process 24(12):5706–5722MathSciNetCrossRefGoogle Scholar
  6. 6.
    Chang X, Yang Y, Xing E P, Yu Y L (2015) Complex event detection using semantic saliency and nearly-isotonic svm. In: Proc. ICMLGoogle Scholar
  7. 7.
    Chang X, Yu YL, Yang Y, Xing EP (2016) Semantic pooling for complex event analysis in untrimmed videos. IEEE Trans Pattern Anal Mach Intell.
  8. 8.
    Chang X, Ma Z, Yang Y, Zeng Z, Hauptmann A G (2017) Bi-level semantic representation analysis for multimedia event detection. IEEE Trans Cybern 47(5):1180–1197CrossRefGoogle Scholar
  9. 9.
    Chang X, Ma Z, Lin M, Yang Y, Hauptmann A (2017) Feature interaction augmented sparse learning for fast kinect motion detection. IEEE Trans Image Process.
  10. 10.
    Cheng M M, Warrell J, Lin W Y, Zheng S, Vineet V, Crook N (2013) Efficient salient region detection with soft image abstraction. In: Proc. IEEE ICCV, pp 1529–1536Google Scholar
  11. 11.
    Cheng M M, Mitra N J, Huang X, Torr P H S, Hu S (2015) Global contrast based salient region detection. IEEE Trans Pattern Anal Mach Intell 37(3):569–582CrossRefGoogle Scholar
  12. 12.
    Gao Z, Cheong L F, Wang Y X (2014) Block-sparse rpca for salient motion detection. IEEE Trans Pattern Anal Mach Intell 36(10):1975–1987CrossRefGoogle Scholar
  13. 13.
    Hou X, Zhang L (2008) Dynamic visual attention: searching for coding length increments. In: NIPS, pp 681–688Google Scholar
  14. 14.
    Jiang B, Zhang L, Lu H, Yang C, Yang M H (2013) Saliency detection via absorbing Markov chain. In: Proc. IEEE ICCV, pp 1665–1672Google Scholar
  15. 15.
    Kim J, Han D, Tai Y, Kim J (2014) Salient region detection via high-dimensional color transform. In: Proc IEEE CVPR, pp 883–890Google Scholar
  16. 16.
    Lang C, Liu G, Yu J, Yan S (2012) Saliency detection by multitask sparsity pursuit. IEEE Trans Image Process 21(3):1327–1338MathSciNetCrossRefMATHGoogle Scholar
  17. 17.
    Lee B S, Lau C T, Chen Z, Lin C W (2012) Bottom-up saliency detection model based on human visual sensitivity and amplitude spectrum. IEEE Trans Multimed 14(1):187–198CrossRefGoogle Scholar
  18. 18.
    Li X, Lu H, Zhang L, Ruan X, Yang M H (2013) Saliency detection via dense and sparse reconstruction. In: Proc. IEEE ICCV, pp 2976–2983Google Scholar
  19. 19.
    Li H, Lu H, Lin Z, Shen X, Price B (2015) Inner and inter label propagation: salient object detection in the wild. IEEE Trans Image Process 24(10):3176–3186MathSciNetCrossRefGoogle Scholar
  20. 20.
    Li P, Bu J, Yu J, Chen C (2016) Towards robust subspace recovery via sparsity-constrained latent low-rank representation. J Vis Commun Image Represent 37:46–52CrossRefGoogle Scholar
  21. 21.
    Lin Z, Liu R, Su Z (2011) Linearized alternating direction method with adaptive penalty for low-rank representation. In: NIPS, pp 612–620Google Scholar
  22. 22.
    Liu J, Ji S, Ye J (2009) Multi-task feature learning via efficient 2,1 norm minimization. In: UAIGoogle Scholar
  23. 23.
    Liu G, Lin Z, Yu Y (2010) Robust subspace segmentation by low-rank representation. In: Proc ICML, pp 663–670Google Scholar
  24. 24.
    Liu T, Yuan Z, Sun J, Wang J, Zheng N, Tang X, Shum H (2011) Learning to detect a salient object. IEEE Trans Pattern Anal Mach Intell 33(2):353–367CrossRefGoogle Scholar
  25. 25.
    Ma Z, Chang X, Yang Y, Sebe N, Hauptmann A (2017) The many shades of negativity. IEEE Trans Multimed 19(7):1558–1568CrossRefGoogle Scholar
  26. 26.
    Mahadevan V, Vasconcelos N (2009) Saliency-based discriminant tracking. In: Proc IEEE CVPR, pp 1007–1013Google Scholar
  27. 27.
    Margolin R, Tal A, Zelnik-Manor L (2013) What makes a patch distinct? In: Proc IEEE CVPR, pp 1139–1146Google Scholar
  28. 28.
    Peng Y, Ganesh A, Wright J, Xu W, Ma Y (2012) Rasl: robust alignment by sparse and low-rank decomposition for linearly correlated images. IEEE Trans Pattern Anal Mach Intell 34(11):2233–2246CrossRefGoogle Scholar
  29. 29.
    Peng H, Li B, Ling H, Hu W, Xiong W, Maybank SJ (2016) Salient object detection via structured matrix decomposition. IEEE Trans Pattern Anal Mach Intell.
  30. 30.
    Perazzi F, Krähenbühl P, Pritch Y, Hornung A (2012) Saliency filters: contrast based filtering for salient region detection. In: Proc IEEE CVPR, pp 733–740Google Scholar
  31. 31.
    Rabinovich A, Vedaldi A, Galleguillos C, Wiewiora E, Belongie S (2007) Objects in context. In: Proc IEEE ICCV, pp 1–8Google Scholar
  32. 32.
    Ren W Robust dictionary based data representation (Technical report, 2015. Preprint arXiv:1512.03617)
  33. 33.
    Sharma G, Jurie F, Schmid C (2012) Discriminative spatial saliency for image classification. In: Proc IEEE CVPR, pp 3506–3513Google Scholar
  34. 34.
    Shen X, Wu Y (2012) A unified approach to salient object detection via low rank matrix recovery. In: Proc IEEE CVPR, pp 853–860Google Scholar
  35. 35.
    Shi J, Yan Q, Xu L, Jia J (2016) Hierarchical image saliency detection on extended cssd. IEEE Trans Pattern Anal Mach Intell 38(4):717–729CrossRefGoogle Scholar
  36. 36.
    Souly N, Shah M (2016) Visual saliency detection using group lasso regularization in videos of natural scenes. Int J Comput Vis 117(1):93–110MathSciNetCrossRefGoogle Scholar
  37. 37.
    Sun J, Lu H, Liu X (2015) Saliency region detection based on Markov absorption probabilities. IEEE Trans Image Process 24(5):1639–1649MathSciNetCrossRefGoogle Scholar
  38. 38.
    Tong N, Lu H, Zhang Y, Ruan X (2015) Salient object detection via global and local cues. Pattern Recognit 48:3258–3267CrossRefGoogle Scholar
  39. 39.
    Wang J, Yang J, Yu K, Lv F, Huang T, Gong Y (2010) Locality-constrained linear coding for image classification. In: Proc. IEEE CVPR, pp 3360–3367Google Scholar
  40. 40.
    Wang W, Yan Y, Winkler S, Sebe N (2016) Category specific dictionary learning for attribute specific feature selection. IEEE Trans Image Process 25(3):1465–1478MathSciNetCrossRefGoogle Scholar
  41. 41.
    Wang W, Yan Y, Zhang L, Hong R, Sebe N (2016) Collaborative sparse coding for multiview action recognition. IEEE MultiMedia 23(4):80–87CrossRefGoogle Scholar
  42. 42.
    Xie Y, Lu H, Yang M M (2013) Bayesian saliency via low and mid level cues. IEEE Trans Image Process 22(5):1689–1698MathSciNetCrossRefMATHGoogle Scholar
  43. 43.
    Yan J, Zhu M, Liu H, Liu Y (2010) Visual saliency detection via sparsity pursuit. IEEE Signal Process Lett 17(8):739–742CrossRefGoogle Scholar
  44. 44.
    Yan Y, Yang Y, Meng D, Liu G, Tong W, Hauptmann A G, Sebe N (2015) Event oriented dictionary learning for complex event detection. IEEE Trans Image Process 24(6):1867–1878MathSciNetCrossRefGoogle Scholar
  45. 45.
    Yan Y, Ricci E, Subramanian R, Liu G, Lanz O, Sebe N (2016) A multi-task learning framework for head pose estimation under target motion. IEEE Trans Pattern Anal Mach Intell 38(6):1070– 1083CrossRefGoogle Scholar
  46. 46.
    Yan Y, Nie F, Li W, Gao C, Yang Y, Xu D (2016) Image classification by cross-media active learning with privileged information. IEEE Trans Multimed 18 (12):2494–2502CrossRefGoogle Scholar
  47. 47.
    Yang M, Zhang L, Yang J, Zhang D (2013) Regularized robust coding for face recognition. IEEE Trans Image Process 22(5):1753–1766MathSciNetCrossRefMATHGoogle Scholar
  48. 48.
    Yang C, Zhang L, Lu H, Ruan X, Yang M H (2013) Saliency detection via graph-based manifold ranking. In: Proc IEEE CVPR, pp 3166–3173Google Scholar
  49. 49.
    Zhang J, Sclaroff S (2013) Saliency detection: a Boolean map approach. In: Proc IEEE ICCV, pp 153–160Google Scholar
  50. 50.
    Zhang J, Sclaroff S, Lin Z, Shen X, Price B, Mĕch R (2015) Minimum barrier salient object detection at 80fps. In: Proc IEEE ICCVGoogle Scholar
  51. 51.
    Zhang L, Li X, Nie L, Yang Y, Xia Y (2016) Weakly supervised human fixations prediction. IEEE Trans Cybern 46(1):258–269CrossRefGoogle Scholar
  52. 52.
    Zhang D, Han J, Jiang L, Ye S, Chang X (2017) Revealing event saliency in unconstrained video collection. IEEE Trans Image Process 26(4):1746–1758MathSciNetCrossRefGoogle Scholar
  53. 53.
    Zhang T, Liu S, Ahuja N, Yang M H, Ghanem B (2015) Robust visual tracking via consistent low-rank sparse learning. Int J Comput Vis 111(2):171–190CrossRefGoogle Scholar
  54. 54.
    Zhao M, Jiao L, Feng J, Liu T (2014) A simplified low rank and sparse graph for semi-supervised learning. Neurocomputing 140:84–96CrossRefGoogle Scholar
  55. 55.
    Zhou X, Yang C, Yu W (2013) Moving object detection by detecting contiguous outliers in the low-rank representation. IEEE Trans Pattern Anal Mach Intell 35(3):597–610CrossRefGoogle Scholar
  56. 56.
    Zou W, Kpalma K, Liu Z, Ronsin J (2013) Segmentation driven low-rank matrix recovery for saliency detection. In: Proc BMVCGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2017

Authors and Affiliations

  • Huaxin Xiao
    • 1
  • Weiya Ren
    • 2
  • Wei Wang
    • 3
  • Yu Liu
    • 1
  • Maojun Zhang
    • 1
  1. 1.Department of System EngineeringNational University of Defense TechnologyChangshaChina
  2. 2.Department of Management Science and EngineeringOfficers College of Chinese Armed Police ForceChengduChina
  3. 3.Department of Information Engineering and Computer ScienceUniversity of TrentoTrentoItaly

Personalised recommendations