Skip to main content
SpringerLink
Log in

Deep subspace image clustering network with self-expression and self-supervision

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

The subspace clustering algorithms for image datasets apply a self-expression coefficient matrix to obtain the correlation between samples and then perform clustering. However, such algorithms proposed in recent years do not use the cluster labels in the subspace to guide the deep network and do not get an end-to-end feature extraction and trainable clustering framework. In this paper, we propose a self-supervised subspace clustering model with a deep end-to-end structure, which is called Deep Subspace Image Clustering Network with Self-expression and Self-supervision (DSCNSS). The model embeds the self-supervised module into the subspace clustering. In network model training, alternating iterative optimization is applied to realize the mutual promotion of the self-supervised module and the subspace clustering module. Additionally, we design a new self-supervised loss function to improve the overall performance of the model further. To verify the performance of the proposed method, we conducted experimental tests on standard image datasets such as Extended Yale B, COIL20, COIL100, and ORL. The experimental results show that the performance of the proposed method is better than the existing traditional subspace clustering algorithm and deep clustering algorithm.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. MacQueen J (1967) Some methods for classification and analysis of multivariate observations. In: Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, vol 1, no 14, pp 281–297, Oakland, CA, USA

  2. Ester M, Kriegel H-P, Sander J, Xu X (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. kdd 96(34):226–231

  3. Johnson SC (1967) Hierarchical clustering schemes. Psychometrika 32(3):241–254

  4. Koga H, Ishibashi T, Watanabe T (2007) Fast agglomerative hierarchical clustering algorithm using Locality-Sensitive Hashing. Knowl Inf Syst 12(1):25–53

    Article  MATH  Google Scholar 

  5. Lu H, Song Y, Wei H (2020) Multiple-kernel combination fuzzy clustering for community detection. Soft Comput 24(18):14157–14165

  6. Peng X, Feng J, Xiao S, Yau W-Y, Zhou JT, Yang S (2018) Structured autoencoders for subspace clustering. IEEE Trans Image Process 27(10):5076–5086

  7. Peng X, Feng J, Zhou JT, Lei Y, Yan S (2020) Deep subspace clustering. IEEE Trans Neural Netw Learn Syst 31(12):5509–5521

  8. Zhou P, Hou Y, Feng J (2018) Deep adversarial subspace clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1596–1604

  9. Liu M, Wang Y, Sun J, Ji Z (2021) Adaptive low-rank kernel block diagonal representation subspace clustering. Appl Intell 52(2):2301–2316

  10. Yang X, Deng C, Liu X, Nie F (2018) New l 2, 1-norm relaxation of multi-way graph cut for clustering. In: Thirty-Second AAAI Conference on Artificial Intelligence

  11. Ng AY, Jordan MI, Weiss Y (2002) On spectral clustering: Analysis and an algorithm. In: Advances in neural information processing systems, pp 849–856

  12. Elhamifar E, Vidal R (2013) Sparse subspace clustering: Algorithm, theory, and applications. IEEE Trans Pattern Anal Mach Intell 35(11):2765–2781

  13. Vidal EER (2009) Sparse subspace clustering. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol 6, pp 2790–2797

  14. Liu G, Lin Z, Yu Y (2010) Robust subspace segmentation by low-rank representation. In: Icml, vol 1, p 8, Citeseer

  15. You C, Li C-G, Robinson DP, Vidal R et al (2016) Oracle based active set algorithm for scalable elastic net subspace clustering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3928–3937

  16. Lu H, Liu S, Wei H, Tu J (2020) Multi-kernel fuzzy clustering based on auto-encoder for fMRI functional network. Expert Syst Appl 159:113513

  17. Yang J, Liang J, Wang K, Rosin PL, Yang M-H (2019) Subspace clustering via good neighbors. IEEE Trans Pattern Anal Mach Intell 42(6):1537–1544

    Article  Google Scholar 

  18. Zhang J et al (2019) Self-supervised convolutional subspace clustering network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 5473–5482

  19. Liu M, Wang Y, Sun J, Ji Z (2020) Structured block diagonal representation for subspace clustering. Appl Intell 50(8):2523–2536

  20. Mi Y, Ren Z, Mukherjee M, Huang Y, Sun Q, Chen L (2021) Diversity and consistency embedding learning for multi-view subspace clustering. Appl Intell 51(10):6771–6784

  21. Patel VM, Vidal R (2014) Kernel sparse subspace clustering. In: IEEE International conference on image processing (ICIP). IEEE, pp 2849–2853

  22. Huang Q, Zhang Y, Peng H, Dan T, Weng W, Cai H (2020) Deep subspace clustering to achieve jointly latent feature extraction and discriminative learning. Neurocomputing 404:340–350

  23. Zhang Y et al (2021) Deep multiview clustering via iteratively self-supervised universal and specific space learning. IEEE Trans Cybern (99):1–13

  24. Ji P, Zhang T, Li H, Salzmann M, Reid I (2017) Deep subspace clustering networks. Advances in neural information processing systems, pp 24–33

  25. Valanarasu JMJ, Patel VM (2021) Overcomplete deep subspace clustering networks. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp 746–755

  26. Sun X, Cheng M, Min C, Jing L (2019) Self-supervised deep multi-view subspace clustering. In: Asian Conference on Machine Learning. PMLR, pp 1001–1016

  27. Masci J, Meier U, Cireşan D, Schmidhuber J (2011) Stacked convolutional auto-encoders for hierarchical feature extraction. In: International conference on artificial neural networks. Springer, Berlin, pp 52–59

  28. Ji P, Salzmann M, Li H (2014) Efficient dense subspace clustering. In: IEEE Winter Conference on Applications of Computer Vision. IEEE, pp 461–468

  29. Georghiades AS, Belhumeur PN, Kriegman DJ (2001) From few to many: Illumination cone models for face recognition under variable lighting and pose. IEEE Trans Pattern Anal Mach Intell 23(6):643–660

  30. Samaria FS, Harter AC (1994) Parameterisation of a stochastic model for human face identification. In: Proceedings of 1994 IEEE workshop on applications of computer vision. IEEE, pp 138–142

  31. Nene SA (1996) Columbia object image library (coil-100). Technical Report 6

  32. You C, Robinson D, Vidal R (2016) Scalable sparse subspace clustering by orthogonal matching pursuit. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3918–3927

  33. Vidal R, Favaro P (2014) Low rank subspace clustering (LRSC). Pattern Recogn Lett 43:47–61

  34. Baek S, Yoon G, Song J, Yoon SM (2021) Deep self-representative subspace clustering network. Pattern Recogn 118:108041

  35. Lu H, Chen C, Wei H (2022) Improved deep convolutional embedded clustering with re-selectable sample training. Pattern Recognit 127:108611

Download references

Acknowledgements

This work was supported by the National Science Foundation of China under Grant 61976108 and the Postgraduate Research & Practice Innovation Program of Jiangsu Province (Project No. SJCX20_1416).

Author information

Authors and Affiliations

  1. School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, China

    Chao Chen, Hu Lu & Xia Geng

  2. Jiangsu Province Big Data Ubiquitous Perception and Intelligent Agricultural Application Engineering Research Center, Zhenjiang, China

    Hu Lu

  3. School of Computer Science, Fudan University, Shanghai, China

    Hui Wei

Authors
  1. Chao Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hu Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hui Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xia Geng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hu Lu.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, C., Lu, H., Wei, H. et al. Deep subspace image clustering network with self-expression and self-supervision. Appl Intell 53, 4859–4873 (2023). https://doi.org/10.1007/s10489-022-03654-6

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-03654-6

Keywords

Search

Navigation