Abstract
Convolutional Neural Networks (CNN) has achieved great success in the area of image recognition, but it usually needs sufficient training data. Meanwhile, similar images tend to deliver compact CNN features, so the original CNN features of different images of each subject or similar subjects should have the low-rank and sparse characteristics. Moreover, CNN features may contain redundant information and noise. To this end, we investigate how to discover the robust low-rank and sparse CNN features and show how these features behave for image classification, specifically for the case that the number of training data is relatively small. Specifically, we perform the robust neighborhood preserving low-rank and sparse recovery step over the original CNN features so that salient key information can be extracted and the included noise can also be removed. To demonstrate the effectiveness of the computed joint low-rank and sparse CNN features on image classification, three deep networks, i.e., VGG, Resnet and Alexnet, are evaluated. The simulation results on two widely-used image databases (CIFAR-10 and SVHN) show that the extracted joint low-rank and sparse CNN features can indeed obtain the enhanced results, compared with the original CNN features.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Liu, G., Lin, Z., Yan, S.: Robust recovery of subspace structures by low-rank representation. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 171–184 (2013)
Liu, G., Lin, Z., Yu, Y.: Robust subspace segmentation by low-rank representation. In: Proceedings of the 27th International Conference on Machine Learning (ICML), pp. 663–670 (2010)
Candès, E.J., Li, X., Ma, Y., Wright, J.: Robust principal component analysis. J. ACM (JACM) 58(3), 1–37 (2011)
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images (2009)
Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp. 1097–1105 (2012)
Zhang, Z., Li, F., Zhao, M., Zhang, L., Yan, S.: Joint low-rank and sparse principal feature coding for enhanced robust representation and visual classification. IEEE Trans. Image Process. 25(6), 2429–2443 (2016)
Lin, Z., Ganesh, A., Wright, J., Wu, L., Chen, M., Ma, Y.: Fast convex optimization algorithms for exact recovery of a corrupted low-rank matrix. In: Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), vol.61. June 2009
Lin, Z., Chen, M., Y, Ma.: The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices, pp. 1009–5055 (2010)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Chen, J., Yi, Z.: Sparse representation for face recognition by discriminative low-rank matrix recovery. J. Vis. Commun. Image Represent. 25(5), 763–773 (2014)
Zhang, Y., Jiang, Z.L., Davis, S.: Learning structured low-rank representations for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 676–683 (2013)
Ma, L., Wang, C., Xiao, B., Zhou, W.: Sparse representation for face recognition based on discriminative low-rank dictionary learning. In: Proceedings of the International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2586–2593 (2012)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. (2014)
Cai, J.F., Candès, E.J., Shen, Z.: A singular value thresholding algorithm for matrix completion. SIAM J. Optim. 20(4), 1956–1982 (2010)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Lin, M., Chen, Q., Yan, S.C.: Network in network. In: Proceedings of International Conference on Learning Representations (2013)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge, MA (2016)
Guo, Y., Hastie, T., Tibshirani, R.: Regularized linear discriminant analysis and its application in microarrays. Biostatistics 8(1), 86–100 (2007)
Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)
Hu, Y., Zhang, D., Ye, J., Li, X., He, X.: Fast and accurate matrix completion via truncated nuclear norm regularization. IEEE Trans on Pattern Analysis Machine Intelligence 35(9), 2117–2130 (2013)
Zhang, H., Lin, Z., Zhan, C., Gao, J.: Robust latent low rank representation for subspace clustering. Neurocomputing 145, 369–373 (2014)
Sim, T., Baker, S., Bsat, M.: The CMU pose, illumination, and expression database. IEEE Trans. Pattern Anal. Mach. Intell. 25(12), 1615–1618 (2003)
Lin, Z., Chen, M., Wu, L., Ma, Y.: The augmented Lagrange multiplier method for exact recovery of corrupted low-rank matrices. University of Illinois Urbana-Champaign, Champaign, IL, USA, Tech. (2009)
Netzer, Y., Wang, T., Coates, A.: Reading digits in natural images with unsupervised feature learning. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning, vol. 2011, No. 2, p. 5 (2011)
Nasrabadi, N.M.: Pattern recognition and machine learning. J. Electron. Imaging 16(4), 049901 (2007)
Zhang, Z., Li, F.Z., Zhao, M., Zhang, L., Yan, S.C.: Robust neighborhood preserving projection by Nuclear/L2,1-Norm regularization for image feature extraction. IEEE Trans. Image Process. 26, 1607–1622 (2017)
Zhang, Z., Zhao, M., Li, F.Z., Zhang, L., Yan, S.C.: Robust alternating low-rank representation by joint Lp- and L2, p-norm Minimization. Neural Netw. 96, 55–70 (2017)
Zhang, Z., Yan, S.C., Zhao, M., Li, F.Z.: Bilinear low-rank coding framework and extension for robust image recovery and feature representation. Knowl.-Based Syst. 86, 143–157 (2015)
Zhang, Z., Yan, S.C., Zhao, M.: Similarity preserving low-rank representation for enhanced data representation and effective subspace learning. Neural Netw. 53, 81–94 (2014)
Zhang, H., Patel, V.M.: Convolutional sparse and low-rank coding-based image decomposition. IEEE Trans. Image Process. 27, 2121–2133 (2018)
Zhang, H., Patel, V.M.: Convolutional sparse and low-rank coding-based rain streak removal. WACV, pp. 1259–1267 (2017)
Ongie, G., Jacob, M.: A fast algorithm for convolutional structured low-rank matrix recovery. IEEE Trans. Comput. Imaging 3, 535–550 (2017)
Jaderberg, M., Vedaldi, A., Zisserman, A.: Speeding up Convolutional Neural Networks with Low Rank Expansions. BMVC (2014)
Acknowledgments
This work is partially supported by the National Natural Science Foundation of China (61672365), Major Program of Natural Science Foundation of the Jiangsu Higher Education Institutions of China (15KJA520002), Natural Science Foundation of the Jiangsu Province of China (BK20141195), and the High-Level Talent of “Six Talent Peak” Project of the Jiangsu Province of China (XYDXX-055). Zhao Zhang is the corresponding author of this paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Tang, Z., Zhang, Z., Ma, X., Qin, J., Zhao, M. (2018). Robust Neighborhood Preserving Low-Rank Sparse CNN Features for Classification. In: Hong, R., Cheng, WH., Yamasaki, T., Wang, M., Ngo, CW. (eds) Advances in Multimedia Information Processing – PCM 2018. PCM 2018. Lecture Notes in Computer Science(), vol 11164. Springer, Cham. https://doi.org/10.1007/978-3-030-00776-8_33
Download citation
DOI: https://doi.org/10.1007/978-3-030-00776-8_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00775-1
Online ISBN: 978-3-030-00776-8
eBook Packages: Computer ScienceComputer Science (R0)