Zhao Zhang
Shuicheng Yan
Skip Abstract Section
Abstract
Low-rank coding-based representation learning is powerful for discovering and recovering the subspace structures in data, which has obtained an impressive performance; however, it still cannot obtain deep hidden information due to the essence of single-layer structures. In this article, we investigate the deep low-rank representation of images in a progressive way by presenting a novel strategy that can extend existing single-layer latent low-rank models into multiple layers. Technically, we propose a new progressive Deep Latent Low-Rank Fusion Network (DLRF-Net) to uncover deep features and the clustering structures embedded in latent subspaces. The basic idea of DLRF-Net is to progressively refine the principal and salient features in each layer from previous layers by fusing the clustering and projective subspaces, respectively, which can potentially learn more accurate features and subspaces. To obtain deep hidden information, DLRF-Net inputs shallow features from the last layer into subsequent layers. Then, it aims at recovering the hierarchical information and deeper features by respectively congregating the subspaces in each layer of the network. As such, one can also ensure the representation learning of deeper layers to remove the noise and discover the underlying clean subspaces, which will be verified by simulations. It is noteworthy that the framework of our DLRF-Net is general and is applicable to most existing latent low-rank representation models, i.e., existing latent low-rank models can be easily extended to the multilayer scenario using DLRF-Net. Extensive results on real databases show that our framework can deliver enhanced performance over other related techniques.
- Y. Bengio, A. Courville, and P. Vincent. 2013. Representation learning: A review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell 35, 8 (2013), 1798–1828. DOI:https://doi.org/10.1109/TPAMI.2013.50 Google Scholar
Digital Library
- J. Cunningham and Z. Ghahramani. 2015. Linear dimensionality reduction: Survey, insights, and generalizations. J. Mach. Learn. Res. 16, 1 (2015), 2859–2900. DOI:https://doi.org/10.12681/eadd/19088 Google ScholarDigital Library
- F. Wang and J. Sun. 2015. Survey on distance metric learning and dimensionality reduction in data mining. Data Min. Knowl. Discov 29, 2 (2015), 534–564. DOI:https://doi.org/10.1007/s10618-014-0356-z Google ScholarDigital Library
- J. Wright, Y. Ma, and J. Mairal. 2010. Sparse representation for computer vision and pattern recognition. Proc. IEEE 98, 6 (2010), 1031–1044. DOI:https://doi.org/10.1007/978-1-4471-6714-3_8Google ScholarCross Ref
- G. Liu, Z. Lin, and S. C. Yan. 2013. Robust recovery of subspace structures by low-rank representation. IEEE Trans. Pattern Anal. Mach. Intell 35, 1 (2013), 171–184. DOI:https://doi.org/10.1109/TPAMI. 2012.88 Google ScholarDigital Library
- F. Fomin, P. Golovach, and F. Panolan. 2020. Parameterized low-rank binary matrix approximation. Data Min. Knowl. Discov 34, 2 (2020), 478–532. DOI:https://doi.org/10.1007/s10618-019-00669-5Google ScholarDigital Library
- E. J. Candès, X. Li, and Y. Ma. 2011. Robust principal component analysis?. J. ACM 58, 3 (2011), 1–11. DOI:https://doi.org/10.1145/1970392.1970395Google ScholarDigital Library
- B. K. Bao, G. C. Liu, and C. Xu. 2012. Inductive robust principal component analysis. IEEE Trans. Image Process. 21, 8 (2012), 3794–3800. DOI:https://doi.org/10.1109/TIP.2012.2192742 Google ScholarDigital Library
- G. C. Liu and S. C. Yan. 2011. Latent low-rank representation for subspace segmentation and feature extraction. In Proceedings of the IEEE Conference on Computer Vision. 1615–1622. DOI:https://doi.org/10.1109/ICCV.2011.6126422 Google ScholarDigital Library
- Z. Zhang, S. C. Yan, and M. B. Zhao. 2014. Similarity preserving low-rank representation for enhanced data representation and effective subspace learning. Neural Networks 53 (2014), 81–94. DOI:https://doi. org/10.1016/j.neunet.2014.01.001Google ScholarCross Ref
- Z. Zhang, F. Li, M. Zhao, L. Zhang, and S. Yan. 2016. Joint low-rank and sparse principal feature coding for enhanced robust representation and visual classification. IEEE Trans. Image Process. 25, 6 (2016), 2429–2443. DOI:https://doi.org/10.1109/TIP.2016.2547180 Google ScholarDigital Library
- S. Yu and Y. Wu. 2018. Subspace clustering based on latent low rank representation with Frobenius norm minimization. Neurocomputing 275 (2018), 2479–2489. DOI:https://doi.org/10.1016/j.neucom.2017.11.021 Google ScholarDigital Library
- Z. Lin, M. Chen, L. Wu, and Y. Ma. 2009. The augmented Lagrange multiplier method for exact recovery of corrupted low-rank matrices. Technical Report UILU-ENG-09-2215. DOI:https://doi.org/10.1016/j.jsb. 2012.10.010Google Scholar
- H. Zhang, Z. C. Lin, C. Zhang, and J. Gao. 2014. Robust latent low rank representation for subspace clustering. Neurocomputing 145 (2014), 369–373. DOI:https://doi.org/10.1016/j.neucom.2014.05.022Google ScholarCross Ref
- J. Ren, Z. Zhang, S. Li, Y. Wang, G. Liu, S. Yan, and M. Wang. 2019. Learning hybrid representation by robust dictionary learning in factorized compressed space. IEEE Trans. Image Process. 29, 1 (2020), 3941–3956. DOI:10.1109/TIP.2020.2965289Google ScholarCross Ref
- P. He, X. Xu, J. Ding, and B. Fan. 2020. Low-rank nonnegative matrix factorization on Stiefel manifold. Inf. Sci. 514 (2020), 131–148. DOI:https://doi.org/10.1016/j.ins.2019.12.004Google ScholarDigital Library
- C. Hou, F. P. Nie, X. L. Li, D.Y. Yi, and Yi Wu. 2014. Joint embedding learning and sparse regression: A framework for unsupervised feature selection. IEEE Trans. Cybern. 44, 6 (2014), 793–804. DOI:https://doi.org/10.1109/TCYB.2013.2272642Google ScholarCross Ref
- L. Ma, C. H. Wang, B. H. Xiao, and W. Zhou. 2012. Sparse representation for face recognition based on discriminative low-rank dictionary learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2586–2593. DOI: https://doi.org/10.1109/CVPR.2012.6247977. Google ScholarDigital Library
- L. Y. Li, S. Li, and Y. Fu. 2014. Learning low-rank and discriminative dictionary for image classification. Image Vis. Comput. 32, 10 (2014), 814–823. DOI:https://doi.org/10.1016/j.imavis.2014.02.007Google ScholarCross Ref
- Y. Zhang, Z. L. Jiang, and L. Davis. 2013. Learning structured low-rank representations for image classification. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition 2013, 676–683. DOI:https://doi.org/10.1109/cvpr.2013.93 Google ScholarDigital Library
- J. Chen and Z. Yi. 2014. Sparse representation for face recognition by discriminative low-rank matrix recovery. J. Vis. Commun. Image R 25, 5 (2014), 763–773. DOI:https://doi.org/10.1016/j.jvcir.2014.01.015Google ScholarCross Ref
- J. Xie, J. Yang, J. Qian, Y. Tai, and H. Zhang. 2017. Robust nuclear norm-based matrix regression with applications to robust face recognition. IEEE Trans. Image Process. 26, 5 (2017), 2286–2295. DOI:https://doi.org/10.1109/TIP.2017.2662213 Google ScholarDigital Library
- Z. Xue, J. Du, D. Du, and S. Lyu. 2019. Deep low-rank subspace ensemble for multi-view clustering. Inf. Sci. 482 (2019), 210–227. DOI:https://doi.org/10.1016/j.ins.2019.01.018Google ScholarDigital Library
- Z. Li and J. Tang. 2017. Weakly-supervised deep nonnegative low-rank model for social image tag refinement and assignment. In Proceedings of AAAI Conference on Artificial Intelligence. 4154–4160. DOI:https://dlacm.xilesou.top/doi/10.5555/3298023.3298171 Google ScholarDigital Library
- J. Zhao, Y. Lv, Z. Zhou, and F. Cao. 2017. A novel deep learning algorithm for incomplete face recognition: Low-rank-recovery network. Neural Networks 94 (2017), 115–124. DOI: https://doi.org/10.1016/j.neunet.2017.06.013.Google ScholarCross Ref
- J. Cai, E. Candès, and Z. Shen. 2010. A singular value thresholding algorithm for matrix completion. SIAM J. Opt. 20, 4 (2010), 1956–1982. DOI:https://doi.org/10.1137/080738970Google ScholarDigital Library
- J. Shi and J. Malik. 2000. Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22, 8 (2000), 888–905. Google ScholarDigital Library
- S. A. Nene, S. K. Nayar, and H. Murase. 1996. Columbia object image library (COIL-20). Technical Report CUCS-005-96.Google Scholar
- L. Wang, B. Wang, Z. Zhang, Q. Yue, L. Fu, G. Liu, and M. Wang. 2019. Robust auto-weighted projective low-rank and sparse recovery for visual representation. Neural Networks 117 (2019), 201–215. DOI:https://doi.org/10.1016/j.neunet.2019.05.007 Google ScholarDigital Library
- Z. Zhang, M. Zhao, F. Li, L. Zhang, and S. Yan. 2017. Robust alternating low-rank representation by joint Lp- and L2,p-norm minimization. Neural Networks 96 (2017), 55–70. DOI:https://doi.org/10.1016/j.neunet.2017.08.001Google ScholarDigital Library
- Z. Zhang, J. Ren, S. Li, R. Hong, Z. Zha, and M. Wang. 2019. Robust subspace discovery by block-diagonal adaptive locality-constrained representation. In Proceedings of the ACM International Conference on Multimedia. 1569–1577. DOI:https://doi.org/10.1145/3343031.3351023 Google ScholarDigital Library
- J. Hull. 1994. A database for handwritten text recognition research. IEEE Trans. Pattern Anal. Mach. Intell. 16, 5 (1994), 550–554. DOI:10.1109/34.291440 Google ScholarDigital Library
- Z. Song, K. Cui, and G. Cheng. 2020. Image set face recognition based on extended low rank recovery and collaborative representation. Int. J. Mach. Learn. Cybern. 11, 1 (2020), 71–80. DOI:https://doi.org/10.1007/s13042-019-00941-6Google ScholarCross Ref
- Z. Zhang, L.Wang, S. Li, Y. Wang, Z. Zhang, Z. Zha, and M. Wang. 2019. Adaptive structure-constrained robust latent low-rank coding for image recovery. In Proceedings of the 19th IEEE International Conference on Data Mining.Google Scholar
- Y. Lu, Z. Lai, W. Wong, and X. Li. 2020. Low-rank discriminative regression learning for image classification. Neural Networks 125 (2020), 245–257. DOI:https://doi.org/10.1016/j.neunet.2020.02.007Google ScholarCross Ref
- H. Li and Z. Lin. 2020. Provable accelerated gradient method for nonconvex low rank optimization. Mach. Learn. 109, 1 (2020), 103–134. DOI:https://doi.org/10.1007/s10994-019-05819-wGoogle ScholarCross Ref
- X. Lan, S. Zhang, P. C. Yuen, and R. Chellappa. 2018. Learning common and feature-specific patterns: A novel multiple-sparse-representation based tracker. IEEE Trans. Image Process. 27, 4 (2018), 2022–2037. DOI:https://doi.org/10.1109/TIP.2017.2777183Google ScholarCross Ref
- F. V. Fomin, P. A. Golovach, D. Lokshtanov, F. Panolan, and S. Saurabh. 2020. Approximation schemes for low-rank binary matrix approximation problems. ACM Trans. Algorithms 16, 1 (2020), 12:1–12:39. DOI:https://doi.org/10.1145/3365653 Google ScholarDigital Library
- D. Graham and N. Allinson. 1998. Characterizing virtual eigensignatures for general purpose face recognition. In Face Recognition: From Theory to Application (NATO ASI Series F, Computer and Systems Sciences). Springer, Berlin, 446–456.Google Scholar
- A. Georghiades, P. Belhumeur, and D. Kriegman. 2001. From few to many: Illumination cone models for face recognition under variable lighting and pose. IEEE Trans. Pattern Anal. Mach. Intell. 23, 6 (2001), 643–660. DOI:https://doi.org/10.1109/34.927464 Google ScholarDigital Library
- T. Sim, S. Baker, and M. Bsat. 2003. The CMU pose, illuminlation, and expression database. IEEE Trans. Pattern Anal. Mach. Intell. 25, 12 (2003), 1615–1618. DOI:https://doi.org/10.1109/afgr.2002.1004130 Google ScholarDigital Library
- B. Weyrauch, J. Huang, B. Heisele, and V. Blanz. 2004. Component-based face recognition with 3D morphable models. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 85–85. DOI:https://doi.org/10.1109/CVPR.2004.315 Google ScholarDigital Library
- J. Li, H. Chang, J. Yang, W. Luo, and Y. Fu. 2017. Visual representation and classification by learning group sparse deep stacking network. IEEE Transactions . Image Process. 27, 1 (2017), 464–476. DOI:https://doi.org/10.1109/tip.2017.2765833/12234Google ScholarCross Ref
- H. Xiao, K. Rasul, and R. Vollgraf. 2017. Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms. arXiv:1708.07747v2.Google Scholar
- J. Li and H. Liu. 2017. Projective low-rank subspace clustering via learning deep encoder. In Proceedings of the International Joint Conferences on Artificial Intelligence. 2145–2151. DOI:https://doi.org/10.24963/ijcai.2017/298 Google ScholarDigital Library
- X. Chen, J. Li, Y. Song, F. Li, J. Chen, and K. Yang. 2019. Low-rank tensor completion for image and video recovery via capped nuclear norm. IEEE Access. 7 (2019), 112142–112153. DOI:https://doi.org/10.1109/access.2019.2934482Google ScholarCross Ref
- F. Su, H. Y. Shang, and J. Y. Wang. 2019. Low-rank deep convolutional neural network for multitask learning. Comput. Intell. Neurosci. 2019, 7410701:1–7410701:10. DOI:https://doi.org/10.1155/2019/7410701Google Scholar
- Z. Ding and Y. Fu. 2018. Deep transfer low-rank coding for cross-domain learning. IEEE Trans. Neural Netw. Learning Syst. 30, 6 (2018), 1768–1779. DOI:https://doi.org/10.1109/tnnls.2018.2874567Google ScholarCross Ref
- C. Lu, X. Peng, and Y. Wei. 2019. Low-rank tensor completion with a new tensor nuclear norm induced by invertible linear transforms. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5996–6004. DOI:https://doi.org/10.1109/cvpr.2019.00615Google Scholar
- Y. Chen, X. Xiao, and Y. Zhou. 2020. Low-rank quaternion approximation for color image processing. IEEE Trans. Image Process. 29 (2020), 1426–1439. DOI:https://doi.org/10.1109/tip.2019.2941 319Google ScholarCross Ref
- A. Acharya, R. Goel, A. Metallinou, and I. S. Dhillon. 2019. Online embedding compression for text classification using low rank matrix factorization. In Proceedings of th eAAAI Conference on Artificial Intelligence. 6196–6203. DOI:https://doi.org/10.1609/aaai.v33i01.33016196Google Scholar
- J. Kim, J. Sim, and C. Kim. 2015. Video deraining and desnowing using temporal correlation and low-rank matrix completion. IEEE Trans. Image Process. 24, 9 (2015), 2658–2670. DOI:10.1109/TIP. 2015.2428933Google ScholarDigital Library
- H. Zhang and V. Patel. 2017. Convolutional sparse and low-rank coding-based rain streak removal. In Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 1259–1267. DOI:https://doi.org/10.1109/WACV.2017.145Google Scholar
- B. Kim, H. Kim, K. Kim, S. Kim, and J. Kim. 2019. Learning not to learn: Training deep neural networks with biased data. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 9012–9020. DOI:https://doi.org/10.1109/cvpr.2019.00922Google Scholar
- Y. Wang, X. Lin, L. Wu, W. Zhang, Q. Zhang, and X. Huang. 2015. Robust subspace clustering for multi-view data by exploiting correlation consensus. IEEE Trans. Image Process. 24, 11 (2015), 3939–3949. DOI:10.1109/TIP.2015.2457339Google ScholarDigital Library
- Y. Wang, L. Wu, X. Lin, and J. Gao. 2018. Multiview spectral clustering via structured low-rank matrix factorization. IEEE Trans. Neural Netw. Learning Syst. 29, 10 (2018), 4833–4843. DOI:10.1109/TNNLS.2017.2777489Google ScholarCross Ref
- P. Giampouras, A. Rontogiannis, and K. Koutroumbas. 2019. Alternating iteratively reweighted least squares minimization for low-rank matrix factorization. IEEE Trans. Signal Process. 67, 2 (2019), 490–503. DOI:10.1109/TSP.2018.2883921Google ScholarDigital Library
- Z. Zhang, J. Ren, Z. Zhang, and G. Liu. 2020. Deep latent low-rank fusion network for progressive subspace discovery. In Proceedings of the International Joint Conferences on Artificial Intelligence. 1–8.Google Scholar
- Z. Kang, X. Zhao, C. Peng, H. Zhu, J. T. Zhou, X. Peng, W. Chen, and Z. Xu. 2020. Partition level multiview subspace clustering. Neural Networks 122 (2019), 279–288. DOI:https://doi.org/10.1016 /j.ne unet.2019.10.010Google ScholarCross Ref
- Z. Kang, G. Shi, S. Huang, W. Chen, X. Pu, J. T. Zhou, and Z. Xu. 2020. Multi-graph fusion for multi-view spectral clustering. Knowledge-Based Syst. 189 (2020), 105102. DOI:10.1016/j.knosys.2019.105102Google ScholarDigital Library
- Z. Kang, H. Pan, S. Hoi, and Z. Xu. 2019. Robust graph learning from noisy data. IEEE Trans. Cybern. 2019, 1–11. DOI:10.1109/TCYB.2018.2887094Google Scholar
Index Terms
- DLRF-Net: A Progressive Deep Latent Low-Rank Fusion Network for Hierarchical Subspace Discovery
Recommendations
Deep latent low-rank fusion network for progressive subspace discovery
IJCAI'20: Proceedings of the Twenty-Ninth International Joint Conference on Artificial IntelligenceLow-rank representation is powerful for recovering and clustering the subspace structures, but it cannot obtain deep hierarchical information due to the single-layer mode. In this paper, we present a new and effective strategy to extend the single-layer ...
Laplacian regularized deep low-rank subspace clustering network
AbstractSelf-expression-based deep subspace clustering, integrating traditional subspace clustering methods into deep learning paradigm to enhance the representative capacity, has become an important branch in unsupervised learning methods. However, most ...
Learnable low-rank latent dictionary for subspace clustering
Highlights- We propose a unified framework to integrate linear or nonlinear feature extraction and subspace clustering.
Graphical abstractDisplay Omitted
AbstractRecently, Self-Expressive-based Subspace Clustering (SESC) has been widely applied in pattern clustering and machine learning as it aims to learn a representation that can faithfully reflect the correlation between data points. However,...
Comments