Advertisement

Enhancing Feature Representation for Saliency Detection

  • Tao Zheng
  • Bo LiEmail author
  • Haobo Rao
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11555)

Abstract

Current detectors for saliency detection adopt deep convolutional neural networks to continuously improve accuracy, but the results are still not satisfactory. We propose Multiple Receptive Field Aggregating Module (MRFAM) that can capture abundant context information to enhance feature representation. We assemble it into a novel network to predict saliency maps. Extensive experiments on six benchmark datasets demonstrate that the module is efficient and our proposed network can accurately capture salient objects with sharp boundaries in complex scene, performing favorably against the state-of-the-art methods in term of different evaluation metrics.

Keywords

Saliency detection Deep learning Feature representation 

Notes

Acknowledgments

This research was supported by the National Natural Science Foundation of China (Grant Nos. 11627802, 51678249), by State Key Lab of Subtropical Building Science, South China University Of Technology (2018ZB33), and by the State Scholarship Fund of China Scholarship Council (201806155022)

References

  1. 1.
    Borji, A., Frintrop, S., Sihite, D.N., Itti, L.: Adaptive object tracking by learning background context. In: IEEE Computer Vision and Pattern Recognition Workshops, pp. 23–30 (2012)Google Scholar
  2. 2.
    Siagian, C., Itti, L.: Rapid biologically-inspired scene classification using features shared with visual attention. IEEE Trans. Pattern Anal. Mach. Intell. 29(2), 300–312 (2007)Google Scholar
  3. 3.
    He, J., et al.: Mobile product search with bag of hash bits and boundary reranking. In: IEEE Computer Vision and Pattern Recognition, pp. 3005–3012 (2012)Google Scholar
  4. 4.
    Bi, S., Li, G., Yu, Y.: Person re-identification using multiple experts with random subspaces. J. Image Graph. 2(2), 151–157 (2014)Google Scholar
  5. 5.
    Zhu, W., Liang, S., Wei, Y., Sun, J.: Saliency optimization from robust background detection. In: IEEE Computer Vision and Pattern Recognition, pp. 2814–2821 (2014)Google Scholar
  6. 6.
    Yang, C., Zhang, L., Lu, H., Ruan, X., Yang, M.H.: Saliency detection via graph-based manifold ranking. In: IEEE Computer Vision and Pattern Recognition, pp. 3166–3173 (2013)Google Scholar
  7. 7.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)Google Scholar
  8. 8.
    Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: IEEE Computer Vision and Pattern Recognition, pp. 5987–5995 (2017)Google Scholar
  9. 9.
    Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Computer Vision and Pattern Recognition, pp. 1–9 (2015)Google Scholar
  10. 10.
    Zhang, L., Dai, J., Lu, H., He, Y., Wang, G.: A bi-directional message passing model for salient object detection. In: IEEE Computer Vision and Pattern Recognition, pp. 1741–1750 (2018)Google Scholar
  11. 11.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar
  12. 12.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  13. 13.
    Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)
  14. 14.
    Hou, Q., Cheng, M.M., Hu, X., Borji, A., Tu, Z., Torr, P.: Deeply supervised salient object detection with short connections. In: IEEE Computer Vision and Pattern Recognition, pp. 5300–5309 (2017)Google Scholar
  15. 15.
    Liu, N., Han, J., Yang, M.H.: PiCANet: learning pixel-wise contextual attention for saliency detection. In: IEEE Computer Vision and Pattern Recognition, pp. 3089–3098 (2018)Google Scholar
  16. 16.
    Zhang, P., Wang, D., Lu, H., Wang, H., Ruan, X.: Amulet: aggregating multi-level convolutional features for salient object detection. In: IEEE International Conference on Computer Vision, pp. 202–211 (2017)Google Scholar
  17. 17.
    Li, G., Yu, Y.: Deep contrast learning for salient object detection. In: IEEE Computer Vision and Pattern Recognition, pp. 478–487 (2016)Google Scholar
  18. 18.
    Liu, N., Han, J.: Dhsnet: deep hierarchical saliency network for salient object detection. In: IEEE Computer Vision and Pattern Recognition, pp. 678–686 (2016)Google Scholar
  19. 19.
    Lee, G., Tai, Y.W., Kim, J.: Deep saliency with encoded low level distance map and high level features. In: IEEE Computer Vision and Pattern Recognition, pp. 660–668 (2016)Google Scholar
  20. 20.
    Luo, Z., Mishra, A.K., Achkar, A., Eichel, J.A., Li, S., Jodoin, P.M.: Non-local deep features for salient object detection. In: IEEE Computer Vision and Pattern Recognition, pp. 6609–6617 (2017)Google Scholar
  21. 21.
    Wang, L., Wang, L., Lu, H., Zhang, P., Ruan, X.: Saliency detection with recurrent fully convolutional networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 825–841. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46493-0_50Google Scholar
  22. 22.
    Wang, T., Borji, A., Zhang, L., Zhang, P., Lu, H.: A stagewise refinement model for detecting salient objects in images. In: IEEE International Conference on Computer Vision, pp. 4019–4028 (2017)Google Scholar
  23. 23.
    Zhang, P., Wang, D., Lu, H., Wang, H., Yin, B.: Learning uncertain convolutional features for accurate saliency detection. In: IEEE International Conference on Computer Vision, pp. 212–221 (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of Electronics and Information EngineeringSouth China University of TechnologyGuangzhouChina

Personalised recommendations