Saliency Detection Based on Unsupervised SDAE Network

被引：0
|
作者：
Li Q.-W. [1 ,2 ]
Ma Y.-P. [1 ,2 ]
Zhou Y.-Q. [1 ,2 ]
Xing J. [1 ,2 ]
机构：
[1] College of Internet of Things Engineering, Hohai University, Changzhou, 213022, Jiangsu
[2] Changzhou Key Laboratory of Sensor Networks and Environmental Sensing, Changzhou, 213022, Jiangsu
来源：
Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2019年 / 47卷 / 04期
关键词：
Deep belief network (DBN); Mutual information; Saliency detection; Stacked denoising auto-encoder (SDAE); Unsupervised network;
D O I：
10.3969/j.issn.0372-2112.2019.04.015
中图分类号：
学科分类号：
摘要：
The traditional saliency detection method is difficult to detect different kinds of saliency target simultaneously. In order to solve this problem, an algorithm based on unsupervised SDAE network is proposed in this paper. The stacked denoising auto-encoder (SDAE) network is used to sparsely reconstruct original image in multiple scales. The difference between the original image and the reconstructed image is used as a saliency map, and the binaryzation of the saliency map is used as salient detection result. In the process of SDAE network training, the original image is used as the original data and the reconstructed images are treated as observed data. In order to improve the efficiency of network training, the deep belief network (DBN) is trained by greedy method in each layer without supervising, and the network parameters are delivered to stacked denoising auto-encoder (SDAE) network as initial parameters. Then, the mutual information between the original data and the observed data is used as loss function, and the network parameters are tuned by backpropagation. The experiments show that the proposed algorithm can accomplish the saliency detection of various targets, which has the advantages of good universality and high accuracy. © 2019, Chinese Institute of Electronics. All right reserved.
引用
收藏
页码：871 / 879
页数：8
相关论文
共 36 条
  • [1] Ren Z., Gao S., Chia L.T., Et al., Region-based saliency detection and its application in object recognition, IEEE Transactions on Circuits & Systems for Video Technology, 24, 5, pp. 769-779, (2014)
  • [2] Ding P., Zhang Y., Jia P., Et al., Ship detection on sea surface based on visual saliency, Acta Electronica Sinica, 46, 1, pp. 127-134, (2018)
  • [3] Yang X., Qian X., Xue Y., Scalable mobile image retrieval by exploring contextual saliency, IEEE Transactions on Image Processing, 24, 6, pp. 1709-1721, (2015)
  • [4] Feng S.-H., Lang C.-Y., Xu D., Combining graph learning and region saliency analysis for content-based image retrieval, Acta Electronica Sinica, 39, 10, pp. 2288-2294, (2011)
  • [5] Jiang W., Lu Z.-Y., Li J., Et al., Visual saliency and text confidence map based background suppression for scene text, Acta Electronica Sinica, 43, 9, pp. 62-68, (2015)
  • [6] Song T.-F., Liu Z.-Y., Saliency detection based on center rectangle composition prior, Journal of Image and Graphics, 22, 3, pp. 315-326, (2017)
  • [7] Zhu W., Liang S., Wei Y., Et al., Saliency optimization from robust background detection, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2814-2824, (2014)
  • [8] Li X., Lu H., Zhang L., Et al., Saliency detection via dense and sparse reconstruction, IEEE International Conference on Computer Vision, pp. 2976-2983, (2013)
  • [9] Ma Y.F., Zhang H.J., Contrast-based image attention analysis by using fuzzy growing, Eleventh ACM International Conference on Multimedia, pp. 374-381, (2003)
  • [10] Cheng M.M., Zhang G.X., Mitra N.J., Et al., Global contrast based salient region detection, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 409-416, (2011)
1234