Low-rank weighted co-saliency detection via efficient manifold ranking

  • Tengpeng Li
  • Huihui Song
  • Kaihua ZhangEmail author
  • Qingshan Liu
  • Wei Lian


Co-saliency detection, which aims to detect common salient objects in a group of images, has attracted much attention in the field of computer vision. In this paper, we present an effective co-saliency detection approach that first exploits an efficient manifold ranking scheme to extract a set of co-saliency regions, and then renders rank constraint to the feature matrix of the extracted regions to achieve a high-quality co-saliency map. Specifically, for each input image, we first develop a two-stage manifold ranking algorithm to generate multiple coarse co-saliency maps, and then we extract a group of co-salient regions from each image by fusing the co-saliency maps and the superpixels extracted from it. Then, we design an adaptive weight for each co-saliency map based on the sparse error matrix that is obtained by rendering rank constraint on the feature matrix of the salient regions. Finally, we multiply the coarse co-saliency maps with their corresponding weights to get the fine fusion results, which are further optimized by Graph cuts. Extensive evaluations on the iCoseg dataset demonstrate favorable performance of the proposed approach over some state-of-art methods in terms of both qualitative and quantitative results.


Manifold ranking Color histogram Low-rank constraints Graph cut Co-saliency detection 



This work was supported in part by the National Natural Science Foundation of China under Grant 61876088, Grant 61532009, and Grant 61773002, in part by the Natural Science Foundation of Jiangsu Province under Grant BK20170040.


  1. 1.
    Achanta R, Hemami S, Estrada F, Susstrunk S (2009) Frequency-tuned salient region detection. In: IEEE conference on computer vision and pattern recognition, 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):2274–2282CrossRefGoogle Scholar
  3. 3.
    Batra D, Kowdle A, Parikh D, Luo J, Luo TL (2010) icoseg: Interactive co-segmentation with intelligent scribble guidance. In: IEEE conference on computer vision and pattern recognition, pp 3169–3176. IEEEGoogle Scholar
  4. 4.
    Boykov Y, Kolmogorov V (2001) An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. In: International workshop on energy minimization methods in computer vision and pattern recognition, pp 359–374Google Scholar
  5. 5.
    Boykov Y, Veksler O, Zabih R (2001) Fast approximate energy minimization via graph cuts. IEEE Trans Pattern Anal Mach Intell 23(11):1222–1239CrossRefGoogle Scholar
  6. 6.
    Cao X, Tao Z, Zhang B, Fu H, Feng W (2014) Self-adaptively weighted co-saliency detection via rank constraint. IEEE Trans Image Process 23(9):4175–4186MathSciNetzbMATHGoogle Scholar
  7. 7.
    Cao X, Cheng Y, Tao Z, Fu H (2014) Co-saliency detection via base reconstruction. In: Proceedings of ACM international conference on multimedia, pp 997–1000. ACMGoogle Scholar
  8. 8.
    Cao X, Tao Z, Zhang B, Huazhu F, Li X (2013) Saliency map fusion based on rank-one constraint. In: IEEE international conference on multimedia and expo, pp 1–6Google Scholar
  9. 9.
    Cheng M-M, Mitra NJ, Huang X, Hu S-M (2014) Salientshape: Group saliency in image collections. Vis Comput 30(4):443–453CrossRefGoogle Scholar
  10. 10.
    Fu H, Cao X, Tu Z (2013) Cluster-based co-saliency detection. IEEE Trans Image Process 22(10):3766MathSciNetCrossRefGoogle Scholar
  11. 11.
    Ge C, Keren F, Liu F, Li B, Yang J (2016) Co-saliency detection via inter and intra saliency propagation. Signal Process Image Commun 44:69–83CrossRefGoogle Scholar
  12. 12.
    Huang R, Feng W, Sun J (2015) Saliency and co-saliency detection by low-rank multiscale fusion. In: IEEE international conference on multimedia and expo, pp 1–6Google Scholar
  13. 13.
    Itti L, Koch C, Niebur E (2002) A model of saliency-based visual attention for rapid scene analysis. IEEE Trans Pattern Anal Mach Intell 20(11):1254–1259CrossRefGoogle Scholar
  14. 14.
    Jia Y, Han M (2013) Category-independent object-level saliency detection. In: IEEE international conference on computer vision, pp 1761–1768. IEEEGoogle Scholar
  15. 15.
    Jian M, Qi Q, Dong J, Sun X, Sun Y, Lam K-M (2017) Saliency detection using quaternionic distance based weber local descriptor and level priors. Multi Tools Appl 77:1–18Google Scholar
  16. 16.
    Jian M, Qi Q, Dong J, Yin Y, Lam K-M (2018) Integrating qdwd with pattern distinctness and local contrast for underwater saliency detection. J Vis Commun Image Represent 53:31–41CrossRefGoogle Scholar
  17. 17.
    Li H, Ngan KN (2011) A co-saliency model of image pairs. IEEE Trans Image Process 20(12):3365–3375MathSciNetCrossRefGoogle Scholar
  18. 18.
    Li H, Meng F, Ngan KN (2013) Co-salient object detection from multiple images. IEEE Trans Multimed 15(8):1896–1909CrossRefGoogle Scholar
  19. 19.
    Li L, Liu Z, Zou W, Zhang X, Meur OL (2014) Co-saliency detection based on region-level fusion and pixel-level refinement. In: IEEE international conference on multimedia and expo, pp 1–6Google Scholar
  20. 20.
    Li Y, Keren F, Liu Z, Yang J (2014) Efficient saliency-model-guided visual co-saliency detection. IEEE Signal Process Lett 22(5):588–592CrossRefGoogle Scholar
  21. 21.
    Liu Z, Zou W, Li L, Shen L, Meur OL (2013) Co-saliency detection based on hierarchical segmentation. IEEE Signal Process Lett 21(1):88–92CrossRefGoogle Scholar
  22. 22.
    Ohtsu N (2007) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1):62–66CrossRefGoogle Scholar
  23. 23.
    Partridge M, Jabri M (2002) Robust principal component analysis. In: Proceedings of the IEEE signal processing society workshop on neural networks for signal processing, pp 289–298Google Scholar
  24. 24.
    Qin Y, Lu H, Xu Y, Wang H (2015) Saliency detection via cellular automata. In: IEEE conference on computer vision and pattern recognition, pp 110–119. IEEEGoogle Scholar
  25. 25.
    Wang L, Gao C, Jian J, Tang L, Liu J (2018) Semantic feature based multi-spectral saliency detection. Multimed Tools Appl 77(3):3387–3403CrossRefGoogle Scholar
  26. 26.
    Wei L, Zhao S, El Farouk Bourahla O, Li X, Wu F (2017) Group-wise deep co-saliency detection. In: Proceedings of the 26th international joint conference on artificial intelligence, pp 3041–3047. AAAI PressGoogle Scholar
  27. 27.
    Xiang D, Wang Z (2017) Salient object detection via saliency bias and diffusion. Multimed Tools Appl 76(5):6209–6228CrossRefGoogle Scholar
  28. 28.
    Xu B, Bu J, Chen C, Cai D, He X, Liu W, Luo J (2011) Efficient manifold ranking for image retrieval. In: Proceedings of the 34th international ACM SIGIR conference on research and development in information retrieval, p 525–534. ACMGoogle Scholar
  29. 29.
    Yang C, Zhang L, Huchuan L, Ruan X, Yang MH (2013) Saliency detection via graph-based manifold ranking. In: IEEE conference on computer vision and pattern recognition, pp 3166–3173Google Scholar
  30. 30.
    Zhang D, Huazhu F, Han J, Borji A, Li X (2018) A review of co-saliency detection algorithms: fundamentals, applications, and challenges. ACM Trans Intell Syst Technol 9(4):38CrossRefGoogle Scholar
  31. 31.
    Zhang D, Han J, Li C, Wang J, Li X (2016) Detection of co-salient objects by looking deep and wide. Int J Comput Vis 120(2):215–232MathSciNetCrossRefGoogle Scholar
  32. 32.
    Zhang D, Meng D, Han J (2017) Co-saliency detection via a self-paced multiple-instance learning framework. IEEE Trans Pattern Anal Mach Intell 39 (5):865–878CrossRefGoogle Scholar
  33. 33.
    Zhu W, Liang S, Wei Y, Sun J (2014) Saliency optimization from robust background detection. In: IEEE conference on computer vision and pattern recognition, pp 2814–2821Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Jiangsu Key Laboratory of Big Data Analysis Technology (B-DAT)Nanjing University of Information Science and TechnologyNanjingChina
  2. 2.Department of Computer ScienceChangzhi UniversityChangzhiChina

Personalised recommendations