Subspace Clustering via Block-diagonal Decomposition

FU Zhiqiang; ZHAO Yao; CHANG Dongxia; WANG Yiming

doi:10.23919/cje.2022.00.385

Article Contents

Article Navigation > Chinese Journal of Electronics > 2024 > Uncorrected proof

Zhiqiang FU, Yao ZHAO, Dongxia CHANG, et al., “Subspace Clustering via Block-diagonal Decomposition,” Chinese Journal of Electronics, vol. 33, no. 6, pp. 1–11, 2024 doi: 10.23919/cje.2022.00.385

Citation:

Zhiqiang FU, Yao ZHAO, Dongxia CHANG, et al., “Subspace Clustering via Block-diagonal Decomposition,” Chinese Journal of Electronics, vol. 33, no. 6, pp. 1–11, 2024 doi: 10.23919/cje.2022.00.385

Citation:

PDF( 7138 KB)

Subspace Clustering via Block-diagonal Decomposition

doi: 10.23919/cje.2022.00.385

FU Zhiqiang^{1, 2, 3
,},
ZHAO Yao^{1, 2
,
,},
CHANG Dongxia^{1, 2
,},
WANG Yiming^{1, 2
,}

1.
Institute of Information Science, Beijing Jiaotong University, Beijing 100044, China
2.
Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing 100044, China
3.
China Construction Bank, Beijing 100032, China

More Information

Author Bio:
Zhiqiang FU received the B.S. degree in Beijing Jiaotong University in 2017. He is currently pursuing the Ph.D. degree in Institute of Information Science, Beijing Jiaotong University. His current research interests include pattern recognition and clustering. (Email: fuzhiqiang1230@163.com)

Yao ZHAO received the Ph.D. degree from Beijing Jiaotong University (BJTU), China, in 1996. He is currently the Director of the Institute of Information Science, BJTU. His current research interests include image/video coding, digital watermarking and forensics, video analysis and understanding, and artificial intelligence. He serves or served on the Editorial Boards of several international journals, including as an Associate Editor of the IEEE TRANSACTIONS ON CYBERNETICS and IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, a Senior Associate Editor of the IEEE SIGNAL PROCESSING LETTERS, and an Area Editor of Signal Processing: Image Communication. He was named as a Distinguished Young Scholar by the National Science Foundation of China in 2010. He was also elected as a Chang Jiang Scholar of the Ministry of Education of China in 2013. (Email: yzhao@bjtu.edu.cn)

Dongxia CHANG received the M.S. degree in Mathematics from Xidian University and the Ph.D. degree in Control Science and Engineering from Tsinghua University in 2003 and 2009, respectively. She is currently a professor of the Institute of Information Science of Beijing Jiaotong University. Her research interests include clustering, pattern recognition, and image segmentation. (Email: dxchang@bjtu.edu.cn)

Yiming WANG received the B.E. degree in Computer Science and Technology from the Shandong Normal University, Jinan, China, in 2017, and the M.E. degree in Electronics and Communications Engineering from Beijing Jiaotong University, Beijing, China, in 2019. He is currently working toward the Ph.D. degree in the School of Computer and Information Technology at Beijing Jiaotong University. His current research interests include clustering analysis and deep learning. (Email: wangym@bjtu.edu.cn)
Corresponding author: E-mail: yzhao@bjtu.edu.cn
Received Date: 2022-11-14
Accepted Date: 2023-06-16

Available Online: 2024-03-13

Abstract

Abstract

The subspace clustering has been addressed by learning the block-diagonal self-expressive matrix. This block-diagonal structure heavily affects the accuracy of clustering but is rather challenging to obtain. In this paper, a novel and effective subspace clustering model, i.e., Subspace Clustering via Block-diagonal Decomposition (SCBD), that can simultaneously capture the block-diagonal structure and gain the clustering result is proposed. In our model, a strict block-diagonal decomposition is introduced to directly pursue the k block-diagonal structure corresponding to k clusters. In this novel decomposition, the self-expressive matrix is decomposed into the block indicator matrix to demonstrate the cluster each sample belongs to. Based on the strict block-diagonal decomposition, the block-diagonal shift is proposed to capture the local intra-cluster structure, which shifts the samples in the same cluster to get smaller distances and results in more discriminative features for clustering. Extensive experimental results on synthetic and real databases demonstrate the superiority of SCBD over other state-of-the-art methods.
- Subspace clustering,
- Representation matrix,
- Low-rank representation

FullText(HTML)

References(37)

References

[1]	K. Li and Y. Gao, “Fuzzy clustering with the structural α-entropy,” Chinese Journal of Electronics, vol. 27, no. 6, pp. 1118–1125, 2018. doi: 10.1049/cje.2018.04.004
[2]	S. L. Wang, Q. Li, H. N. Yuan, et al., “Robust clustering with topological graph partition,” Chinese Journal of Electronics, vol. 28, no. 1, pp. 76–84, 2019. doi: 10.1049/cje.2018.09.005
[3]	X. Jiang, B. Y. Zheng, L. Wang, et al., “Clustering for topological interference management,” Chinese Journal of Electronics, vol. 31, no. 5, pp. 844–850, 2022. doi: 10.1049/cje.2021.00.277
[4]	X. Peng, Y. F. Li, I. W. Tsang, et al., “XAI beyond classification: Interpretable neural clustering,” Journal of Machine Learning Research, vol. 23, no. 6, pp. 1–28, 2022.
[5]	Y. F. Li, P. Hu, Z. T. Liu, et al., “Contrastive clustering,” in Proceedings of the 35th AAAI Conference on Artificial Intelligence, Palo Alto, CA, USA, pp. 8547–8555, 2021.
[6]	Y. F. Li, M. X. Yang, D. Z. Peng, et al., “Twin contrastive learning for online clustering,” International Journal of Computer Vision, vol. 130, no. 9, pp. 2205–2221, 2022. doi: 10.1007/s11263-022-01639-z
[7]	C. Tang, X. Z. Zhu, X. W. Liu, et al., “Learning a joint affinity graph for multiview subspace clustering,” IEEE Transactions on Multimedia, vol. 21, no. 7, pp. 1724–1736, 2019. doi: 10.1109/TMM.2018.2889560
[8]	L. S. Zhuang, Z. H. Zhou, S. H. Gao, et al., “Label information guided graph construction for semi-supervised learning,” IEEE Transactions on Image Processing, vol. 26, no. 9, pp. 4182–4192, 2017. doi: 10.1109/TIP.2017.2703120
[9]	J. Xu, M. Y. Yu, L. Shao, et al., “Scaled simplex representation for subspace clustering,” IEEE Transactions on Cybernetics, vol. 51, no. 3, pp. 1493–1505, 2021. doi: 10.1109/TCYB.2019.2943691
[10]	M. J. Sun, S. W. Wang, P. Zhang, et al., “Projective multiple kernel subspace clustering,” IEEE Transactions on Multimedia, vol. 24 pp. 2567–2579, 2022. doi: 10.1109/TMM.2021.3086727
[11]	J. Wen, X. Z. Fang, Y. Xu, et al., “Low-rank representation with adaptive graph regularization,” Neural Networks, vol. 108 pp. 83–96, 2018. doi: 10.1016/j.neunet.2018.08.007
[12]	X. X. Zhang, Z. F. Zhu, Y. Zhao, et al., “Self-supervised deep low-rank assignment model for prototype selection,” in Proceedings of the 27th International Joint Conference on Artificial Intelligence, Stockholm, Sweden, pp. 3141–3147, 2018.
[13]	C. Wang, W. Pedrycz, Z. W. Li, et al., “Residual-driven fuzzy C-means clustering for image segmentation,” IEEE/CAA Journal of Automatica Sinica, vol. 8, no. 4, pp. 876–889, 2021. doi: 10.1109/JAS.2020.1003420
[14]	L. Wei, F. F. Zhang, Z. W. Chen, et al., “Subspace clustering via adaptive least square regression with smooth affinities,” Knowledge-Based Systems, vol. 239, article no. 107950, 2022. doi: 10.1016/j.knosys.2021.107950
[15]	X. J. Chen, W. J. Hong, F. P. Nie, et al., “Enhanced balanced min cut,” International Journal of Computer Vision, vol. 128, no. 7, pp. 1982–1995, 2020. doi: 10.1007/s11263-020-01320-3
[16]	W. K. Wong, N. Han, X. Z. Fang, et al., “Clustering structure-induced robust multi-view graph recovery,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 30, no. 10, pp. 3584–3597, 2020. doi: 10.1109/TCSVT.2019.2945202
[17]	S. W. Wang, X. W. Liu, X. Z. Zhu, et al., “Fast parameter-free multi-view subspace clustering with consensus anchor guidance,” IEEE Transactions on Image Processing, vol. 31 pp. 556–568, 2022. doi: 10.1109/TIP.2021.3131941
[18]	Z. Q. Tao, H. F. Liu, S. Li, et al., “Robust spectral ensemble clustering via rank minimization,” ACM Transactions on Knowledge Discovery from Data, vol. 13, no. 1, article no. 4, 2019. doi: 10.1145/3278606
[19]	L. Wang, B. J. Wang, Z. Zhang, et al., “Robust auto-weighted projective low-rank and sparse recovery for visual representation,” Neural Networks, vol. 117 pp. 201–215, 2019. doi: 10.1016/j.neunet.2019.05.007
[20]	E. Elhamifar and R. Vidal, “Sparse subspace clustering,” in Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, pp. 2790–2797, 2009.
[21]	G. C. Liu, Z. C. Lin, and Y. Yu, “Robust subspace segmentation by low-rank representation,” in Proceedings of the 27th International Conference on International Conference on Machine Learning, Haifa, Israel, pp. 663–670, 2010.
[22]	G. C. Liu and S. C. Yan, “Latent low-rank representation for subspace segmentation and feature extraction,” in Proceedings of 2011 International Conference on Computer Vision, Barcelona, Spain, pp. 1615–1622, 2011.
[23]	L. S. Zhuang, H. Y. Gao, Z. C. Lin, et al., “Non-negative low rank and sparse graph for semi-supervised learning,” in Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, pp. 2328–2335, 2012.
[24]	M. Yin, J. B. Gao, Z. C. Lin, et al., “Dual graph regularized latent low-rank representation for subspace clustering,” IEEE Transactions on Image Processing, vol. 24, no. 12, pp. 4918–4933, 2015. doi: 10.1109/TIP.2015.2472277
[25]	L. K. Fei, Y. Xu, X. Z. Fang, et al., “Low rank representation with adaptive distance penalty for semi-supervised subspace classification,” Pattern Recognition, vol. 67, pp. 252–262, 2017. doi: 10.1016/j.patcog.2017.02.017
[26]	R. W. Zhou, X. J. Chang, L. Shi, et al., “Person reidentification via multi-feature fusion with adaptive graph learning,” IEEE Transactions on Neural Networks and Learning Systems, vol. 31, no. 5, pp. 1592–1601, 2020. doi: 10.1109/TNNLS.2019.2920905
[27]	J. S. Feng, Z. C. Lin, H. Xu, et al., “Robust subspace segmentation with block-diagonal prior,” in Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, pp. 3818–3825, 2014.
[28]	C. Y. Lu, J. S. Feng, Z. C. Lin, et al., “Subspace clustering by block diagonal representation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 2, pp. 487–501, 2019. doi: 10.1109/TPAMI.2018.2794348
[29]	Z. H. Li, F. P. Nie, X. J. Chang, et al., “Dynamic affinity graph construction for spectral clustering using multiple features,” IEEE Transactions on Neural Networks and Learning Systems, vol. 29, no. 12, pp. 6323–6332, 2018. doi: 10.1109/TNNLS.2018.2829867
[30]	Z. H. Li, F. P. Nie, X. J. Chang, et al., “Rank-constrained spectral clustering with flexible embedding,” IEEE Transactions on Neural Networks and Learning Systems, vol. 29, no. 12, pp. 6073–6082, 2018. doi: 10.1109/TNNLS.2018.2817538
[31]	J. B. Shi and J. Malik, “Normalized cuts and image segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 888–905, 2000. doi: 10.1109/34.868688
[32]	F. Wu, Y. L. Hu, J. B. Gao, et al., “Ordered subspace clustering with block-diagonal priors,” IEEE Transactions on Cybernetics, vol. 46, no. 12, pp. 3209–3219, 2016. doi: 10.1109/TCYB.2015.2500821
[33]	J. Wang, J. X. Liu, C. H. Zheng, et al., “A mixed-norm Laplacian regularized low-rank representation method for tumor samples clustering,” IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 16, no. 1, pp. 172–182, 2019. doi: 10.1109/TCBB.2017.2769647
[34]	M. Yin, J. B. Gao, and Z. C. Lin, “Laplacian regularized low-rank representation and its applications,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, no. 3, pp. 504–517, 2016. doi: 10.1109/TPAMI.2015.2462360
[35]	J. Wen, B. Zhang, Y. Xu, et al., “Adaptive weighted nonnegative low-rank representation,” Pattern Recognition, vol. 81 pp. 326–340, 2018. doi: 10.1016/j.patcog.2018.04.004
[36]	Y. P. Zhao, L. Chen, and C. L. P. Chen, “Laplacian regularized nonnegative representation for clustering and dimensionality reduction,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, no. 1, pp. 1–14, 2021. doi: 10.1109/TCSVT.2020.2967424
[37]	Z. Q. Fu, Y. Zhao, D. X. Chang, et al., “A hierarchical weighted low-rank representation for image clustering and classification,” Pattern Recognition, vol. 112, article no. 107736, 2021. doi: 10.1016/j.patcog.2020.107736