Abstract
The robust Gaussian restricted Boltzmann machine can effectively learn the structure of noise to achieve better results in the face denoising task. The robust Gaussian restricted Boltzmann machine model contains two types of the restricted Boltzmann machine (RBM) model, where a general RBM is used to model the structure of the noise and a Gaussian RBM is used to model the clean data. The spike-and-slab RBM shows better learning abilities than the Gaussian RBM in real images modeling. In addition, the deep Boltzmann machine (DBM) shows powerful image reconstruction ability. To model the real images better, we first stack the spike-and-slab RBM and the RBM to create the spike-and-slab DBM. And then, we utilize the spike-and-slab DBM instead of the Gaussian RBM to model the density of the clean data in the Robust Gaussian RBM, and the proposed method is named as the robust spike-and-slab DBM which can obtain clearer denoising images. Finally, in order to obtain better denoising results, we make use of the learned spike-and-slab DBM model and the mean field method to multi-inference the denoising data learned from the robust spike-and-slab DBM. Experimental results show that the robust spike-and-slab DBM is an effective neural network denoising method.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Zhang K, Zuo W, Chen Y, Meng D, Zhang L (2017) Beyond a gaussian denoiser: residual learning of deep cnn for image denoising. IEEE Trans Image Process 26(7):3142–3155
Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2018) Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell 40(4):834–848
Li Z, Tang J, He X (2018) Robust structured nonnegative matrix factorization for image representation. IEEE Trans Neural Netw Learn Syst 29(5):1947–1960
Yang J, Luo L, Qian J, Tai Y, Zhang F, Xu Y (2017) Nuclear norm based matrix regression with applications to face recognition with occlusion and illumination changes. IEEE Trans Pattern Anal Mach Intell 39(1):156–171
Ouyang W, Zeng X, Wang X (2016) Partial occlusion handling in pedestrian detection with a deep model. IEEE Trans Circuits Syst Video Technol 26(11):2123–2137
Hinton G, Salakhutdinov R, Tang Y (2012) Robust Boltzmann machines for recognition and denoising. In: IEEE conference on computer vision and pattern recognition, pp 2264–2271
Shaham U, Cheng X, Dror O, Jaffe A, Nadler B, Chang J, Kluger Y (2016) A deep learning approach to unsupervised ensemble learning. In: International conference on machine learning
Zhang N, Ding S, Zhang J, Xue Y (2018) An overview on restricted Boltzmann machines. Neurocomputing 275:1186–1199
Zhang J, Ding S, Zhang N (2018) An overview on probability undirected graphs and their applications in image processing. Neurocomputing 321:156–168
Cho KH, Ilin A, Raiko T (2011) Improved learning of Gaussian–Bernoulli restricted Boltzmann machines. In: International conference on artificial neural networks. Springer, Berlin, pp 10–17
Ranzato M, Hinton GE (2010) Modeling pixel means and covariances using factorized third-order Boltzmann machines. In: IEEE computer society conference on computer vision and pattern recognition, pp 2551–2558
Courville A, Bergstra J, Bengio Y (2011) A spike and slab restricted Boltzmann machine. In: Proceedings of the fourteenth international conference on artificial intelligence and statistics, pp 233–241
Courville A, Desjardins G, Bergstra J, Bengio Y (2014) The Spike-and-Slab RBM and extensions to discrete and sparse data distributions. IEEE Trans Pattern Anal Mach Intell 36(9):1874–1887
Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504–507
Salakhutdinov RR, Hinton GE (2012) An efficient learning procedure for deep Boltzmann machines. Neural Comput 24(8):1967–2006
Zhang N, Ding SF, Zhang J, Xue Y (2017) Research on point-wise gated deep networks. Appl Soft Comput 52:1210–1221
Hinton GE (2002) Training products of experts by minimizing contrastive divergence. Neural Comput 14(8):1711–1800
Tieleman T, Hinton GE (2009) Using fast weights to improve persistent contrastive divergence. In: Annual international conference on machine learning, Montreal, pp 1033–1040
Phillips PJ, Wechsler H, Huang J, Rauss PJ (1998) The FERET database and evaluation procedure for face-recognition algorithms. Image Vis Comput 16(5):295–306
Sim T, Baker S, Bsat M (2002) The CMU pose, illumination, and expression (PIE) database. In: IEEE international conference on automatic face and gesture recognition, pp 53–58
Channappayya SS, Bovik AC, Jr RWH (2008) Rate bounds on SSIM index of quantized images. IEEE Trans Image Process A Publ IEEE Signal Process Soc 17(9):1624–1639
Coates A, Ng A, Lee H (2011) An analysis of single-layer networks in unsupervised feature learning. In: International conference on artificial intelligence and statistics, pp 215–223
Acknowledgements
This work is supported by the Fundamental Research Funds for the Central Universities (No. 2017XKZD03).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
We declare that we have no significant competing financial, professional, or personal interests that might have influenced the performance or presentation of the work described in this manuscript.
Rights and permissions
About this article
Cite this article
Zhang, N., Ding, S., Zhang, J. et al. Robust spike-and-slab deep Boltzmann machines for face denoising. Neural Comput & Applic 32, 2815–2827 (2020). https://doi.org/10.1007/s00521-018-3866-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-018-3866-6