Abstract
In an image, how to quickly and effectively extract the useful regions named target regions in the scene according to the saliency features such as spatial domain, frequency domain etc. for further analysis of salient object detection is one of the challenging topics in the field of image segmentation. Most of the existing salient target detection methods use convolution network to extract high-order semantic features, combine pyramid pooling model to fuse high-order and low-order semantic features, and use Adam or SGD optimizer to optimize the model to obtain the salient object. However, the traditional convolution network model is not optimized for the model parameters, and finally redundant parameters will appear in the model, which will aggravate the training time and practical application detection time of the model. Although SGD is fast, it will fall into a large number of local suboptimal solutions or saddle points in the process of non-convex error function optimization. Adam has better performance, but the speed is slightly slower then t -> ∞ that will not have a good generalization performance. In order to solve the above problems, a new optimization strategy is proposed to compress the model. At the same time, AdaX, an optimizer with SGD speed and Adam performance, is used to optimize the model. Through the test on the open data set DUTS, ESSCD and etc., the proposed optimization model method reduces the parameters of the original model, and also improves the training speed and application detection speed of the model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Koch, C., Poggio, T.: Predicting the visual world: silence is golden. Nat. Neurosci. 2(1), 9–10 (1999)
Yang, C., Zhang, L., Lu, H., Ruan, X., Yang, M.: Saliency detection via graph-based manifold ranking. In: IEEE Conference on Computer Vision and Pattern Recognition 2013. CVPR, pp. 3166–3173. IEEE Computer Society (2013)
Qin, Y., Lu, H.C., Xu, Y.Q.: Saliency detection via cellular automata. In: IEEE Conference on Computer Vision and Pattern Recognition 2015. CVPR, pp. 110–119. IEEE Computer Society (2015)
Hou,X.D., Zhang, L.Q.: Saliency detection: a spectral residual approach. In: IEEE Conference on Computer Vision and Pattern Recognition 2007. CVPR, pp. 17–22. IEEE Computer Society (2007)
Guo, C.L., Ma, Q., Zhang, L.M.: Spatio-temporal saliency detection using phase spectrum of quaternion fourier transform. In: IEEE Conference on Computer Vision and Pattern Recognition 2008. CVPR, pp. 23–28. IEEE Computer Society (2008)
Guo, C.L., Zhang, L.M.: A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression. IEEE Trans. Image Process. 19(1), 185–198 (2010)
Liu, T., Sun, J., Zheng, N.N.: Learning to detect a salient object. In: IEEE Conference on Computer Vision and Pattern Recognition 2007. CVPR, pp. 17–22. IEEE Computer Society (2007)
Liu, T., Zheng, N.N., Ding, W.: Video attention: learning to detect a salient object sequence. In: 19th International Conference on Pattern Recognition 2008. ICPR, pp. 1–4. IEEE Computer Society (2008)
Tong, N., Lu, H.C., Ruan, X.: Salient object detection via bootstrap learning. In: IEEE Conference on Computer Vision and Pattern Recognition 2015. CVPR, pp. 1884–1892. IEEE Computer Society (2015)
Xu, L., Cui, G.M., Zheng, C.P.: Fusion method of visible and infrared images based on multi-scale decomposition and saliency region extraction. Laser Optoelectron. Prog. 54(11), 1–3 (2017)
Zhu, W.J., Liang, S., Wei, Y.C.: Saliency optimization from robust background detection. In: IEEE Conference on Computer Vision and Pattern Recognition 2014. CVPR, pp. 2814–2821. IEEE Computer Society (2008)
Wang, T., Borji, A., Zhang, L.: A stagewise refinement model for detecting salient objects in images. In: IEEE Conference on Computer Vision and Pattern Recognition 2017. CVPR, pp. 4039–4048. IEEE Computer Society (2017)
Liu, J.J., Hou, Q., Cheng, M.M.: A simple pooling-based design for real-time salient object detection. In: IEEE Conference on Computer Vision and Pattern Recognition 2019. CVPR, pp. 3917–3926. Computer Vision Foundation/IEEE (2019)
Iandola, N.F., Moskewicz, M.W., Ashraf, K., Han, S., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1 MB model size. CoRR abs/1602.07360 (2016)
Li, W., Zhang, Z., Wang, X.: AdaX: Adaptive Gradient Descent with Exponential Long-Term Memory. CoRR abs/2004.09740 (2020)
Kingma, D.P., Ba, J.: Adam: A Method for Stochastic Optimization. ICLR (Poster) (2015)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)
He, K.M., Zhang X.Y., Ren, S.Q., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition 2016. CVPR, pp. 770–778. IEEE Computer Society (2016)
Lee, G., Tai, Y.W., Kim, J.: Deep saliency with encoded low-level distance map and high-level features. In: IEEE Conference on Computer Vision and Pattern Recognition 2016. CVPR, pp. 660–668. IEEE Computer Society (2016)
Liu, T., et al.: Learning to detect a salient object. IEEE Pattern Anal. Mach. Intell. 33(2), 353–367 (2011)
Li, G.B., Yu, Y.Z.: Visual saliency based on multiscale deep features. In: IEEE Conference on Computer Vision and Pattern Recognition 2015. CVPR, pp. 5455–5463. IEEE Computer Society (2015)
Li, G., Xie, Y., Lin, L., Yu, Y.Z.: Instance-level salient object segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition 2017. CVPR, pp. 247–256. IEEE Computer Society (2017)
Hou, Q.B., Cheng, M.M., Hu, X.W., Borji, A., Tu, Z.W., Torr, P.: Deeply supervised salient object detection with short connections. IEEE Trans. Pattern Anal. Mach. Intell. 41(4), 815–828 (2019)
Yan, Q., Xu, L., Shi, J.P., Jia, J.Y.: Hierarchical saliency detection. In: IEEE Conference on Computer Vision and Pattern Recognition 2013. CVPR, pp. 1155–1162. IEEE Computer Society (2013)
Li, Y., Hou, X.D., Koch, C., Rehg, J.M., Yuille, A.L.: The secrets of salient object segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition 2014. CVPR, pp. 280–287. IEEE Computer Society (2014)
Yang, C., Zhang, L.H., Lu, H.C., Ruan, X., Yang, M.H.: Saliency detection via graph-based manifold ranking. In: IEEE Conference on Computer Vision and Pattern Recognition 2013. CVPR, pp. 3166–3173. IEEE Computer Society (2013)
Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 640–651 (2015)
Movahedi, V., Elder, J.H.: Design and perceptual validation of performance measures for salient object segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition 2010. CVPR, pp. 49–56. IEEE Computer Society (2010)
Wang, L.J., et al.: Learning to detect salient objects with image-level supervision. In: IEEE Conference on Computer Vision and Pattern Recognition 2017. CVPR, pp. 3796–3805. IEEE Computer Society (2017)
Xie, S.N., Tu, Z.W.: Holistically-nested edge detection. Int. J. Comput. Vision 125(1–3), 3–18 (2015)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Li, F.F.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition 2009. CVPR, pp. 248–255. IEEE Computer Society (2009)
Acknowledgement
This work is supported by CERNET Innovation Project (NGII20190625).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, B., Wu, Y., Zhang, J., Ma, M. (2021). An Improved CNN Model for Fast Salient Object Detection. In: Sun, X., Zhang, X., Xia, Z., Bertino, E. (eds) Advances in Artificial Intelligence and Security. ICAIS 2021. Communications in Computer and Information Science, vol 1423. Springer, Cham. https://doi.org/10.1007/978-3-030-78618-2_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-78618-2_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-78617-5
Online ISBN: 978-3-030-78618-2
eBook Packages: Computer ScienceComputer Science (R0)