Abstract
Salient object detection is a fundamental problem in both pattern recognition and image processing tasks. Previous salient object detection algorithms usually involve various features based on priors/assumptions about the properties of the objects. Inspired by the effectiveness of recently developed feature learning, we propose a novel deep salient object detection (DSOD) model using the deep residual network (ResNet 152-layers) for saliency computation. In particular, we model the image saliency from both local and global perspectives. In the local feature estimation stage, we detect local saliency by using a deep residual network (ResNet-L) which learns local region features to determine the saliency value of each pixel. In the global feature extraction stage, another deep residual network (ResNet-G) is trained to predict the saliency score of each image based on the global features. The final saliency map is generated by a conditional random field (CRF) to combining the local and global-level saliency map. Our DSOD model is capable of uniformly highlighting the objects-of-interest from complex background while well preserving object details. Quantitative and qualitative experiments on three benchmark datasets demonstrate that our DSOD method outperforms state-of-the-art methods in the salient object detection.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ren, Z., Gao, S., Chia, L.T., Tsang, W.H.: Region-based saliency detection and its application in object recognition. IEEE Trans. Circ. Sys. Video Technol. 24(5), 769–779 (2014)
Wu, L., Shen, C., Hengel, A.V.D.: Personnet: person re-identification with deep convolutional neural networks (2016)
Sung, Y.H., Tseng, W.Y., Lin, P.H., Kang, L.W., Lin, C.Y., Yeh, C.H.: Significance-preserving-guided content-aware image retargeting. In: Pan, J.S., Yang, C.N., Lin, C.C. (eds.) Advances in Intelligent Systems and Applications -, vol. 2. Springer, Heidelberg (2013). doi:10.1007/978-3-642-35473-1_34
Johnson, J., Krishna, R., Stark, M., Li, L., Shamma, D.A., Bernstein, M.S., et al.: Image retrieval using scene graphs (2015)
Marat, S., Guironnet, M., Pellerin, D.: Video summarization using a visual attention model. In: European Signal Processing Conference, pp. 1784–1788. IEEE (2015)
Itti, L., Koch, C.: A saliency-based search mechanism for overt and covert shifts of visual attention. Vis. Res. 40(10), 1489–1506 (2000)
Zhou, Q.: Object-based attention: saliency detection using contrast via background prototypes. Electron. Lett. 50(14), 997–999 (2014)
Goferman, S., Zelnik-Manor, L., Tal, A.: Context-aware saliency detection. IEEE Trans. Pattern Anal. Mach. Intell. 34(10), 1915–1926 (2012)
Kruthiventi, S.S.S., Gudisa, V., Dholakiya, J.H., Babu, R.V.: Saliency unified: a deep architecture for simultaneous eye fixation prediction and salient object segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5781–5790. IEEE Computer Society (2016)
Pan, J., Sayrol, E., Giro-I-Nieto, X., Mcguinness, K., OConnor, N.E.: Shallow and deep convolutional networks for saliency prediction. In: Computer Vision and Pattern Recognition, pp. 598–606. IEEE (2016)
Chen, T., Lin, L., Liu, L., Luo, X., Li, X.: Disc: deep image saliency computing via progressive representation learning. IEEE Trans. Neural Netw. Learn. Syst. 27(6), 1135–1149 (2016)
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P.: Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274 (2012)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59(2), 167–181 (2004)
Zhou, C., Wu, D., Qin, W., Liu, C.: An efficient two-stage region merging method for interactive image segmentation. Comput. Electr. Eng. 54(C), 220–229 (2016)
Li, J., Levine, M.D., An, X., Xu, X., He, H.: Visual saliency based on scale-space analysis in the frequency domain. IEEE Trans. Pattern Anal. Mach. Intell. 35(4), 996–1010 (2013)
Wang, J., Lu, H., Li, X., Tong, N., Liu, W.: Saliency detection via background and foreground seed selection. Neurocomputing 152(C), 359–368 (2015)
Tong, N., Lu, H., Xiang, R., Yang, M.H.: Salient object detection via bootstrap learning. In: Computer Vision and Pattern Recognition, pp. 1884–1892. IEEE (2015)
Tong, N., Lu, H., Zhang, Y., Xiang, R.: Salient object detection via global and local cues. Pattern Recogn. 48(10), 3258–3267 (2015)
Wang, L., Lu, H., Xiang, R., Yang, M.H.: Deep networks for saliency detection via local estimation and global search. In: Computer Vision and Pattern Recognition, pp. 3183–3192. IEEE (2015)
Li, G., Yu, Y.: Visual saliency based on multiscale deep features, pp. 5455–5463 (2015)
Lee, G., Tai, Y.W., Kim, J.: Deep saliency with encoded low level distance map and high level features, pp. 660–668 (2016)
Acknowledgment
This work was supported by the General Program of National Natural Science Foundation of China (NSFC) under Grant No.61572362. This research was also partially supported by the General Program of National Natural Science Foundation of China (NSFC) under Grant No.81571347.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Zhu, D., Luo, Y., Dai, L., Shao, X., Itti, L., Lu, J. (2017). Deep Salient Object Detection via Hierarchical Network Learning. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, ES. (eds) Neural Information Processing. ICONIP 2017. Lecture Notes in Computer Science(), vol 10636. Springer, Cham. https://doi.org/10.1007/978-3-319-70090-8_33
Download citation
DOI: https://doi.org/10.1007/978-3-319-70090-8_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70089-2
Online ISBN: 978-3-319-70090-8
eBook Packages: Computer ScienceComputer Science (R0)