Abstract
Although plenty of saliency detection methods based on CNNs have shown impressive performance, we observe that these methods adopt single-scale convolutional layers as saliency detectors after extracting features to predict saliency maps, which will cause serious missed detection especially those targets having small scales, irregular shapes and sporadic locations in complex scenario of multi-target graphs. In addition, the edges of salient objects predicted by these methods are often confused with their background, causing these partial regions to be very blurred. In order to deal with these issues, we delved into the impact of diverse unified detectors based on convolutional layers and nearest neighbor optimization on saliency detection. It was found that (1) the flattened design contributes to the improvement of accuracy, but due to the inherent characteristics of convolutional layers, it is not the effective way to solve the problems; (2) Nearest neighbor optimization is beneficial to remove background regions from salient objects and restore the missing sections while refining their boundaries, yielding a more reliable final prediction. With the progress of these studies, we built a GeminiNet for accurate saliency detection. Quantitative and qualitative experiments on six benchmark datasets demonstrate that our proposed GeminiNet performs favorably against the state-of-the-art methods under different evaluation metrics.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abdulmunem, A., Lai, Y.K., Sun, X.: Saliency guided local and global descriptors for effective action recognition. Comput. Visual Media 2(1), 97–106 (2016). https://doi.org/10.1007/s41095-016-0033-9
Borji, A., Frintrop, S., Sihite, D.N., Itti, L.: Adaptive object tracking by learning background context. In: 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 23–30. IEEE (2012). https://doi.org/10.1109/cvprw.2012.6239191
Cai, S., Huang, J., Zeng, D., Ding, X., Paisley, J.: MEnet: a metric expression network for salient object segmentation. arXiv preprint arXiv:1805.05638 (2018). https://doi.org/10.24963/ijcai.2018/83
Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2018). https://doi.org/10.1109/tpami.2017.2699184
He, S., Jiao, J., Zhang, X., Han, G., Lau, R.W.: Delving into salient object subitizing and detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1059–1067 (2017). https://doi.org/10.1109/iccv.2017.120
Hou, Q., Cheng, M.M., Hu, X., Borji, A., Tu, Z., Torr, P.: Deeply supervised salient object detection with short connections. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5300–5309. IEEE (2017). https://doi.org/10.1109/cvpr.2017.563
Krähenbühl, P., Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. In: Advances in Neural Information Processing Systems, pp. 109–117 (2011)
Lee, G., Tai, Y.W., Kim, J.: Deep saliency with encoded low level distance map and high level features. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 660–668 (2016). https://doi.org/10.1109/cvpr.2016.78
Li, G., Yu, Y.: Deep contrast learning for salient object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 478–487 (2016). https://doi.org/10.1109/cvpr.2016.58
Liu, N., Han, J.: DHSNet: deep hierarchical saliency network for salient object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 678–686 (2016). https://doi.org/10.1109/cvpr.2016.80
Liu, N., Han, J., Yang, M.H.: PiCANet: learning pixel-wise contextual attention for saliency detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3089–3098 (2018). https://doi.org/10.1109/cvpr.2018.00326
Luo, Z., Mishra, A.K., Achkar, A., Eichel, J.A., Li, S., Jodoin, P.M.: Non-local deep features for salient object detection. In: CVPR, vol. 2, p. 7 (2017). https://doi.org/10.1109/cvpr.2017.698
Ren, Z., Gao, S., Chia, L.T., Tsang, I.W.H.: Region-based saliency detection and its application in object recognition. IEEE Trans. Circuits Syst. Video Technol. 24(5), 769–779 (2014). https://doi.org/10.1109/tcsvt.2013.2280096
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015). https://doi.org/10.1109/cvpr.2015.7298594
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016). https://doi.org/10.1109/cvpr.2016.308
Wang, L., Wang, L., Lu, H., Zhang, P., Ruan, X.: Salient object detection with recurrent fully convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. (2018). https://doi.org/10.1109/tpami.2018.2846598
Wang, T., Borji, A., Zhang, L., Zhang, P., Lu, H.: A stagewise refinement model for detecting salient objects in images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4019–4028 (2017). https://doi.org/10.1109/iccv.2017.433
Yang, M., Yu, K., Zhang, C., Li, Z., Yang, K.: DenseASPP for semantic segmentation in street scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3684–3692 (2018). https://doi.org/10.1109/cvpr.2018.00388
Zeng, Y., Lu, H., Zhang, L., Feng, M., Borji, A.: Learning to promote saliency detectors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1644–1653 (2018). https://doi.org/10.1109/cvpr.2018.00177
Zhang, L., Dai, J., Lu, H., He, Y., Wang, G.: A bi-directional message passing model for salient object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1741–1750 (2018). https://doi.org/10.1109/cvpr.2018.00187
Zhang, P., Wang, D., Lu, H., Wang, H., Ruan, X.: Amulet: aggregating multi-level convolutional features for salient object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 202–211 (2017). https://doi.org/10.1109/iccv.2017.31
Zhang, P., Wang, D., Lu, H., Wang, H., Yin, B.: Learning uncertain convolutional features for accurate saliency detection. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 212–221. IEEE (2017). https://doi.org/10.1109/iccv.2017.32
Acknowledgments
This research was supported by National Key R&D Program of China (No. 2017YFC0806000), by National Natural Science Foundation of China (No. 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).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Zheng, T., Li, B., Zeng, D., Zhou, Z. (2019). Delving into the Impact of Saliency Detector: A GeminiNet for Accurate Saliency Detection. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds) Artificial Neural Networks and Machine Learning – ICANN 2019: Image Processing. ICANN 2019. Lecture Notes in Computer Science(), vol 11729. Springer, Cham. https://doi.org/10.1007/978-3-030-30508-6_28
Download citation
DOI: https://doi.org/10.1007/978-3-030-30508-6_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30507-9
Online ISBN: 978-3-030-30508-6
eBook Packages: Computer ScienceComputer Science (R0)