Skip to main content
SpringerLink
Log in

Deep convolutional self-paced clustering

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Clustering is a crucial but challenging task in data mining and machine learning. Recently, deep clustering, which derives inspiration primarily from deep learning approaches, has achieved state-of-the-art performance in various applications and attracted considerable attention. Nevertheless, most of these approaches fail to effectively learn informative cluster-oriented features for data with spatial correlation structure, e.g., images. To tackle this problem, in this paper, we develop a deep convolutional self-paced clustering (DCSPC) method. Specifically, in the pretraining stage, we propose to utilize a convolutional autoencoder to extract a high-quality data representation that contains the spatial correlation information. Then, in the finetuning stage, a clustering loss is directly imposed on the learned features to jointly perform feature refinement and cluster assignment. We retain the decoder to avoid the feature space being distorted by the clustering loss. To stabilize the training process of the whole network, we further introduce a self-paced learning mechanism and select the most confident samples in each iteration. Through comprehensive experiments on seven popular image datasets, we demonstrate that the proposed algorithm can consistently outperform state-of-the-art rivals.

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

Similar content being viewed by others

References

  1. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556

  2. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions, in IEEE Conference on Computer Vision and Pattern Recognition, pp 1–9

  3. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition, in IEEE Conference on Computer Vision and Pattern Recognition, pp 770–778

  4. Hayashi T, Fujita H, Hernandez-Matamoros A (2021) Less complexity one-class classification approach using construction error of convolutional image transformation network. Inf Sci 560:217–234

    Article  MathSciNet  Google Scholar 

  5. MacQueen J (1967) Some methods for classification and analysis of multivariate observations. In: Berkeley Symposium on Mathematical Statistics and Probability, vol 1(14):281–297. Oakland

  6. Bishop CM (2006) Pattern recognition and machine learning. Springer

  7. Shi J, Malik J (2000) Normalized cuts and image segmentation. IEEE Trans Pattern Anal Mach Intell 22(8):888–905

    Article  Google Scholar 

  8. Wold S, Esbensen K, Geladi P (1987) Principal component analysis. Chemometrics Intell Labor Syst 2(1–3):37–52

    Article  Google Scholar 

  9. Cox TF, Cox MAA (2001) Multidimensional scaling. J R Stat Soc 46(2):1050–1057

    MathSciNet  MATH  Google Scholar 

  10. Xu W, Liu X, Gong Y (2003) Document clustering based on non-negative matrix factorization. In: Annual Conference on Research and Development in Informaion Retrieval. ACM, pp 267– 273

  11. Peng H, Hu Y, Chen J, Wang H, Li Y, Cai H (2020) Integrating Tensor Similarity to Enhance Clustering Performance. IEEE Transactions on Pattern Analysis and Machine Intelligence

  12. Tang Y, Xie Y, Zhang C, Zhang Z, Zhang W (2021) One-step multi-view subspace segmentation via joint skinny tensor learning and latent clustering. IEEE Transactions on Cybernetics. https://doi.org/10.1109/TCYB.2021.3053057

  13. Zhang Y, Yang Y, Li T, Fujita H (2019) A multitask multiview clustering algorithm in heterogeneous situations based on LLE and LE. Knowl-Based Syst 163:776–786

  14. Wang H, Yang Y, Liu B, Fujita H (2019) A study of graph-based system for multi-view clustering. Knowl-Based Syst 16:1009–1019

  15. Deng T, Ye D, Ma R, Fujita H, Xiong L (2020) Low-rank local tangent space embedding for subspace clustering. Inf Sci 508:1–21

  16. Hayashi T, Fujita H (2021) Cluster-based zero-shot learning for multivariate data. J Ambient Intell Human Comput 12:1897–1911

  17. Maaten L. v. d., Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9:2579–2605

    MATH  Google Scholar 

  18. Roweis S, Saul L (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500):2323–6

    Article  Google Scholar 

  19. Hinton G, Salakhutdinov R (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504–507

    Article  MathSciNet  Google Scholar 

  20. Schroff F, Kalenichenko D, Philbin J (2015) A unified embedding for face recognition and clustering. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 815–823

  21. Hershey J, Chen Z, Leroux J, Watanabe S (2016) Deep clustering: Discriminative embeddings for segmentation and separation. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp 31–35

  22. Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366

    Article  Google Scholar 

  23. Bengio Y, Courville A, Vincent P (2013) Representation learning: A review and new perspectives

  24. Bruna J, Mallat S (2013) Invariant scattering convolution networks. IEEE Trans Pattern Anal Mach Intell 35(8):1872–1886

    Article  Google Scholar 

  25. Vincent P, Larochelle H, Lajoie I, Bengio Y, Manzagol P. -A. (2010) Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. J Mach Learn Res 11:3371–3408

    MathSciNet  MATH  Google Scholar 

  26. Guo X, Liu X, Zhu E, Yin J (2017) Deep clustering with convolutional autoencoders. In: International Conference on Neural Information Processing, pp 373–382

  27. Peng X, Xiao S, Feng J, Yau W, Yi Z (2016) Deep subspace clustering with sparsity prior. In: International Joint Conference on Artificial Intelligence

  28. Ji P, Zhang T, Li H, Salzmann M, Reid ID (2017) Deep subspace clustering networks. In: Annual Conference on Neural Information Processing Systems, pp 23–32

  29. Yang J, Parikh D, Batra D (2016) Joint unsupervised learning of deep representations and image clusters. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 5147–5156

  30. Chang J, Wang L, Meng G, Xiang S, Pan C (2017) Deep adaptive image clustering. In: International Conference on Computer Vision, pp 5880–5888

  31. Li F, Qiao H, Zhang B (2017) Discriminatively boosted image clustering with fully convolutional auto-encoders. Pattern Recogn 83:161–173

    Article  Google Scholar 

  32. Xie J, Girshick R, Farhadi A (2016) Unsupervised deep embedding for clustering analysis. In: International Conference on Machine Learning, pp 478–487

  33. Guo X, Gao L, Liu X, Yin J (2017) Improved deep embedded clustering with local structure preservation. In: International Joint Conference on Artificial Intelligence, pp 1753–1759

  34. Yang B, Fu X, Sidiropoulos ND, Hong M (2017) Towards kmeans-friendly spaces: Simultaneous deep learning and clustering. Int Conf Mach Learn 70:3861–3870

    Google Scholar 

  35. Fard MM, Thonet T, Gaussier E (2020) Deep k-means: Jointly clustering with k-means and learning representations. Pattern Recognition Letters

  36. Guo X, Zhu E, Liu X, Yin J (2018) Deep embedded clustering with data augmentation. In: Asian Conference on Machine Learning, pp 550–565

  37. Guo X, Liu X, Zhu E, Zhu X, Li M, Xu X, Yin J (2020) Adaptive self-paced deep clustering with data augmentation. IEEE Trans Knowl Data Eng 32(9):1680–1693

    Google Scholar 

  38. Bo D, Wang X, Shi C, Zhu M, Lu E, Cui P (2020) Structural deep clustering network in international world wide web conferences

  39. Ren Y, Hu K, Dai X, Pan L, Hoi SCH, Xu Z (2019) Semi-supervised deep embedded clustering. Neurocomputing 325:121–130

  40. Ren Y, Wang N, Li M, Xu Z (2020) Deep density-based image clustering. Knowledge-Based Systems

  41. 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

  42. Chen R, Tang Y, Zhang C, Zhang W, Hao Z (2021) Deep multi-network embedded clustering. Pattern Recogn Artif Intell 34(1):14–24

    Google Scholar 

  43. Khan F, Mutlu B, Zhu X (2011) How do humans teach: On curriculum learning and teaching dimension. In: Annual Conference on Neural Information Processing Systems, pp 1449–1457

  44. Kumar MP, Packer B, Koller D (2010) Self-paced learning for latent variable models. In: Annual Conference on Neural Information Processing Systems, pp 1189–1197

  45. Tang Y, Xie Y, Yang X, Niu J, Zhang W (2021) Tensor multi-elastic kernel self-paced learning for time series clustering. IEEE Trans Knowl Data Eng 33(3):1223–1237

    Google Scholar 

  46. Jiang L, Meng D, Zhao Q, Shan S, Hauptmann AG (2015) Self-paced curriculum learning. In: AAAI Conference on Artificial Intelligence

  47. Pi T, Li X, Zhang Z, Meng D, Wu F, Xiao J, Zhuang Y (2016) Self-paced boost learning for classification. In: International Joint Conference on Artificial Intelligence

  48. Ren Y, Zhao P, Sheng Y, Yao D, Xu Z (2017) Robust softmax regression for multi-class classification with self-paced learning. In: International Joint Conference on Artificial Intelligence

  49. Pan L, Ai S, Ren Y, Xu Z (2020) Self-paced deep regression forests with consideration on underrepresented examples. In: European Conference on Computer Vision

  50. Ren Y, Huang S, Zhao P, Han M, Xu Z (2020) Self-paced and auto-weighted multi-view clustering. Neurocomputing 383:248–256

  51. Meng D, Zhao Q, Jiang L (2017) A theoretical understanding of self-paced learning. Inf Sci 414:319–328

  52. LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324

    Article  Google Scholar 

  53. Hull JJ (1994) A database for handwritten text recognition research. IEEE Trans Pattern Anal Mach Intell 16(5):550– 554

    Article  Google Scholar 

  54. Han X, Rasul K, Vollgraf R (2017) Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv:1708.07747v2

  55. de Campos TE, Babu BR, Varma M (2009) Character recognition in natural images. In: International Conference on Computer Vision Theory and Applications, Lisbon

  56. Nene SA, Nayar SK, Murase H (1996) Columbia object image library (COIL-20). Technical report CUCS-006-96

  57. Nene SA, Nayar SK, Murase H (February 1996) Columbia object image library (COIL-100), Technical report CUCS-006-96

  58. Kuhn HW (1955) The hungarian method for the assignment problem. Naval Res Logist Quart 2(1):83–97

    Article  MathSciNet  Google Scholar 

  59. Li T, Ding C (2006) The relationships among various nonnegative matrix factorization methods for clustering. In: International Conference on Data Mining, pp 362–371

  60. Strehl A, Ghosh J (2002) Cluster ensembles — a knowledge reuse framework for combining multiple partitions. J Mach Learn Res 3:583–617

    MathSciNet  MATH  Google Scholar 

  61. Hubert L, Arabie P (1985) Comparing partitions. J Classif 2(1):193–218

    Article  Google Scholar 

  62. Rand WM (1971) Objective criteria for the evaluation of clustering methods. J Am Stat Assoc 66(336):846–850

    Article  Google Scholar 

  63. Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. J Mach Learn Res 9:249– 256

    Google Scholar 

  64. Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. J Mach Learn Res 15:315–323

    Google Scholar 

  65. Kingma D, Ba J (2014) Adam: A method for stochastic optimization, arXiv:1412.6980

  66. Ma Z, Lai Y, Kleijn W, Song Y, Wang L, Guo J (2018) Variational bayesian learning for dirichlet process mixture of inverted dirichlet distributions in non-gaussian image feature modeling. IEEE Trans Neural Netw Learn Syst 30:449–463

    Article  MathSciNet  Google Scholar 

Download references

Acknowledgements

The authors are thankful for the financial support in part by the Key-Area Research and Development Program of Guangdong Province (2019B010153002), by the National Natural Science Foundation of China (U1936206, 61806202, 61803087, 61803086), by the Feature Innovation Project of Guangdong Province Department of Education (2019KTSCX192), by the Guangdong Basic and Applied Basic Research Fund (2020B1515310003), and by the Foshan Core Technology Research Project (1920001001367). Rui Chen and Yongqiang Tang contribute equally to this article.

Author information

Authors and Affiliations

  1. Department of Automation, Foshan University, Foshan, China

    Rui Chen & Caixia Zhang

  2. Research Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences, Beijing, China

    Rui Chen, Yongqiang Tang, Lei Tian & Wensheng Zhang

  3. School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China

    Lei Tian & Wensheng Zhang

Authors
  1. Rui Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yongqiang Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lei Tian
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Caixia Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Wensheng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Yongqiang Tang or Caixia Zhang.

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, R., Tang, Y., Tian, L. et al. Deep convolutional self-paced clustering. Appl Intell 52, 4858–4872 (2022). https://doi.org/10.1007/s10489-021-02569-y

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-021-02569-y

Keywords

Search

Navigation