Skip to main content
Springer Nature Link
Log in

Leveraging self-paced learning and deep sparse embedding for image clustering

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Deep clustering outperforms traditional methods by incorporating feature learning. However, some existing deep clustering methods overlook the suitability of the learned features for clustering, leading to insufficient feedback received by the clustering model and hampering the accuracy improvement. To tackle these issues, we propose a joint self-paced learning and deep sparse embedding for image clustering. Our method consists of two stages: pretraining and finetuning. In the pretraining stage, the autoencoder learns basic features and constructs the feature space. In the finetuning stage, method performs two tasks: feature learning and cluster assignment. Specifically, we finetune the encoder with both original and augmented data to preserve the local structure in the feature space. Self-paced learning guarantees that the most confident features are used for each iteration and mitigates the influence of boundary samples. Furthermore, sparse embedding ensures that the model encodes only key features in feature learning tasks, thereby avoiding incorrect calculations resulting from redundant features. Finally, we jointly optimize these two tasks to complete the feature learning for clustering. Extensive experiments on various datasets demonstrate that our approach outperforms existing solutions.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Algorithm 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data availibility

The data that support the findings of this study are available on request from the corresponding author, upon reasonable request.

Notes

  1. http://www.cad.zju.edu.cn/home/dengcai/Data/MLData.html.

References

  1. Feng X, Wu S (2021) Robust sparse coding via self-paced learning for data representation. Inf Sci 546:448–468. https://doi.org/10.1016/j.ins.2020.08.097

    Article  MathSciNet  Google Scholar 

  2. Forest F, Lebbah M, Azzag H, Lacaille J (2021) Deep embedded self-organizing maps for joint representation learning and topology-preserving clustering. Neural Comput Appl 33(24):17439–17469. https://doi.org/10.1007/s00521-021-06331-w

    Article  Google Scholar 

  3. Cai J, Wang S, Guo W (2021) Unsupervised embedded feature learning for deep clustering with stacked sparse auto-encoder. Expert Syst Appl 186:115729. https://doi.org/10.1016/j.eswa.2021.115729

    Article  Google Scholar 

  4. Hu W, Chen C, Ye F, Zheng Z, Du Y (2021) Learning deep discriminative representations with pseudo supervision for image clustering. Inf Sci 568:199–215. https://doi.org/10.1016/j.ins.2021.03.066

    Article  MathSciNet  Google Scholar 

  5. MacQueen J (1967) Some methods for classification and analysis of multivariate observations. Proceedings of the fifth Berkeley symposium on mathematical statistics and probability 1:281–297

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

    Google Scholar 

  7. Shi J, Malik J (2000) Normalized cuts and image segmentation. IEEE Trans Pattern Anal Mach Intell 22(8):888–905. https://doi.org/10.1109/34.868688

    Article  Google Scholar 

  8. Zhou P, Du L, Li X (2021) Self-paced consensus clustering with bipartite graph. In: International joint conferences on artificial intelligence, pp. 2133–2139. AAAI Press, Yokohama, Yokohama, Japan. https://doi.org/10.24963/ijcai.2020/295

  9. Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958. https://doi.org/10.5555/2627435.2670313

    Article  MathSciNet  Google Scholar 

  10. Guo X, Liu X, Zhu E, Yin J (2017) Deep clustering with convolutional autoencoders. In: International conference on neural information processing, pp. 373–382. Springer, Cham. https://doi.org/10.1007/978-3-319-70096-0_39

  11. Le QV, Karpenko A, Ngiam J, Ng AY (2011) Ica with reconstruction cost for efficient overcomplete feature learning. In: Proceedings of the 24th international conference on neural information processing systems, pp. 1017–1025. Curran Associates Inc., Granada, Spain. https://doi.org/10.5555/2986459.2986573

  12. Zou WY, Zhu S, Ng AY, Yu K (2012) Deep learning of invariant features via simulated fixations in video. In: Proceedings of the 25th international conference on neural information processing systems - Volume 2, pp. 3203–3211. Curran Associates Inc., Red Hook, NY, USA. https://doi.org/10.5555/2999325.2999492

  13. Guo X, Liu X, Zhu E, Zhu X, Li M, Xu X, Yin J (2019) Adaptive self-paced deep clustering with data augmentation. IEEE Trans Knowl Data Eng 32(9):1680–1693. https://doi.org/10.1109/TKDE.2019.2911833

    Article  Google Scholar 

  14. Caron M, Bojanowski P, Joulin A, Douze M (2018) Deep clustering for unsupervised learning of visual features. In: Proceedings of the European conference on computer vision, pp. 132–149. https://doi.org/10.48550/arXiv.1807.05520

  15. Song C, Huang Y, Liu F, Wang Z, Wang L (2014) Deep auto-encoder based clustering. Intell Data Anal 18(6):65–76. https://doi.org/10.3233/IDA-140709

    Article  Google Scholar 

  16. Xie J, Girshick R, Farhadi A (2016) Unsupervised deep embedding for clustering analysis. In: International conference on machine learning, pp. 478–487. PMLR, New York. https://proceedings.mlr.press/v48/xieb16.html

  17. 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. AAAI Press, Melbourne, Australia. https://doi.org/10.24963/ijcai.2017/243

  18. Yang B, Fu X, Sidiropoulos ND, Hong M (2017) Towards k-means-friendly spaces: simultaneous deep learning and clustering. In: International conference on machine learning, pp. 3861–3870. PMLR, New York. https://proceedings.mlr.press/v70/yang17b.html

  19. Fard MM, Thonet T, Gaussier E (2020) Deep k-means: jointly clustering with k-means and learning representations. Pattern Recogn Lett 138:185–192. https://doi.org/10.1016/j.patrec.2020.07.028

    Article  ADS  Google Scholar 

  20. Ghasedi Dizaji K, Herandi A, Deng C, Cai W, Huang H (2017) Deep clustering via joint convolutional autoencoder embedding and relative entropy minimization. In: Proceedings of the IEEE international conference on computer vision, pp. 5736–5745. https://doi.org/10.48550/arXiv.1704.06327

  21. Lv J, Kang Z, Lu X, Xu Z (2021) Pseudo-supervised deep subspace clustering. IEEE Trans Image Process 30:5252–5263. https://doi.org/10.1109/TIP.2021.3079800

    Article  ADS  PubMed  Google Scholar 

  22. Kang Z, Lin Z, Zhu X, Xu W (2022) Structured graph learning for scalable subspace clustering: from single view to multiview. IEEE Trans Cybern 52(9):8976–8986. https://doi.org/10.1109/TCYB.2021.3061660

    Article  PubMed  Google Scholar 

  23. Mukherjee S, Asnani H, Lin E, Kannan S (2019) Clustergan: latent space clustering in generative adversarial networks. In: Proceedings of the AAAI conference on artificial intelligence, vol. 33, pp. 4610–4617. AAAI Press, Honolulu, Hawaii, USA. https://doi.org/10.1609/aaai.v33i01.33014610

  24. Kumar M, Packer B, Koller D (2010) Self-paced learning for latent variable models. In: Proceedings of the 23rd international conference on neural information processing systems, pp. 1189–1197. Curran Associates Inc, Vancouver, British Columbia, Canada. https://doi.org/10.5555/2997189.2997322

  25. Xu C, Tao D, Xu C (2015) Multi-view self-paced learning for clustering. In: International joint conference on artificial intelligence, pp. 3974–3980. AAAI Press, Buenos Aires, Argentina. https://doi.org/10.5555/2832747.2832803

  26. Li J, Kang Z, Peng C, Chen W (2021) Self-paced two-dimensional pca. AAAI Conf Artif Intell 35:8392–8400. https://doi.org/10.1609/aaai.v35i9.17020

    Article  Google Scholar 

  27. Sztemberg-Lewandowska M (2006) Principal components in regression analysis. Prace Naukowe-akademii EkonomiczneJ Imienia Oskara Langego We Wroclawiu 1123:50. https://doi.org/10.1007/0-387-22440-8_8

    Article  Google Scholar 

  28. Gu J, Jiao L, Yang S, Liu F (2017) Fuzzy double c-means clustering based on sparse self-representation. IEEE Trans Fuzzy Syst 26(2):612–626. https://doi.org/10.1109/TFUZZ.2017.2686804

    Article  Google Scholar 

  29. Sun X, Qu Q, Nasrabadi NM, Tran TD (2013) Structured priors for sparse-representation-based hyperspectral image classification. IEEE Geosci Remote Sens Lett 11(7):1235–1239. https://doi.org/10.1109/LGRS.2013.2290531

    Article  ADS  Google Scholar 

  30. Zheng M, Bu J, Chen C, Wang C, Zhang L, Qiu G, Cai D (2010) Graph regularized sparse coding for image representation. IEEE Trans Image Process 20(5):1327–1336. https://doi.org/10.1109/TIP.2010.2090535

    Article  MathSciNet  ADS  PubMed  Google Scholar 

  31. Gao S, Tsang IW-H, Chia L-T (2012) Laplacian sparse coding, hypergraph laplacian sparse coding, and applications. IEEE Trans Pattern Anal Mach Intell 35(1):92–104. https://doi.org/10.1109/TPAMI.2012.63

    Article  Google Scholar 

  32. Yang M, Zhang L, Feng X, Zhang D (2011) Fisher discrimination dictionary learning for sparse representation. In: Proceedings of the 2011 international conference on computer vision, pp. 543–550. IEEE Computer Society, USA. https://doi.org/10.1109/ICCV.2011.6126286

  33. Luo W, Li J, Yang J, Xu W, Zhang J (2017) Convolutional sparse autoencoders for image classification. IEEE Trans Neural Netw Learn Syst 29(7):3289–3294. https://doi.org/10.1109/TNNLS.2017.2712793

    Article  MathSciNet  PubMed  Google Scholar 

  34. Moradi R, Berangi R, Minaei B (2020) A survey of regularization strategies for deep models. Artif Intell Rev 53(6):3947–3986. https://doi.org/10.1007/s10462-019-09784-7

    Article  Google Scholar 

  35. Huang G, Liu Z, Pleiss G, Lvd Maaten, Weinberger KQ (2022) Convolutional networks with dense connectivity. IEEE Trans Pattern Anal Mach Intell 44(12):8704–8716. https://doi.org/10.1109/TPAMI.2019.2918284

    Article  PubMed  Google Scholar 

  36. Antoniou A, Storkey AJ, Edwards H (2017) Data augmentation generative adversarial networks. CoRR. https://doi.org/10.48550/arXiv.1711.04340

  37. Wang Y, Huang G, Song S, Pan X, Xia Y, Wu C (2022) Regularizing deep networks with semantic data augmentation. IEEE Trans Pattern Anal Mach Intell 44(7):3733–3748. https://doi.org/10.1109/TKDE.2019.2911833

    Article  PubMed  Google Scholar 

  38. Guo X, Zhu E, Liu X, Yin J (2018) Deep embedded clustering with data augmentation. In: Proceedings of The 10th Asian conference on machine learning, vol. 95, pp. 550–565. https://proceedings.mlr.press/v95/guo18b.html

  39. Abavisani M, Naghizadeh A, Metaxas D, Patel V (2020) Deep subspace clustering with data augmentation. Adv Neural Inf Process Syst 33:10360–10370. https://doi.org/10.5555/3495724.3496593

    Article  Google Scholar 

  40. LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324. https://doi.org/10.1109/5.726791

    Article  Google Scholar 

  41. Jain AK (2010) Data clustering: 50 years beyond k-means. Pattern Recogn Lett 31(8):651–666. https://doi.org/10.1016/j.patrec.2009.09.011

    Article  ADS  Google Scholar 

  42. Jiang Z, Zheng Y, Tan H, Tang B, Zhou H (2017) Variational deep embedding: an unsupervised and generative approach to clustering. In: Proceedings of the 26th international joint conference on artificial intelligence, pp. 1965–1972. AAAI Press, Melbourne, Australia. https://doi.org/10.5555/3172077.3172161

  43. Diallo B, Hu J, Li T, Khan GA, Liang X, Zhao Y (2021) Deep embedding clustering based on contractive autoencoder. Neurocomputing 433:96–107. https://doi.org/10.1016/j.neucom.2020.12.094

    Article  Google Scholar 

  44. Cao L, Asadi S, Zhu W, Schmidli C, Sjöberg M (2021) Simple, scalable, and stable variational deep clustering. In: Machine Learning and Knowledge Discovery in Databases, Ghent, Belgium, pp. 108–124. https://doi.org/10.1007/978-3-030-67658-2_7

Download references

Acknowledgements

We are grateful to the reviewers for their detailed and helpful comments, which allowed us to greatly improve this paper. This work was supported by National Natural Science Foundation of China (62273290, 62072391, 61572419), Natural Science Foundation of Shandong Province (ZR2020MF148).

Author information

Authors and Affiliations

  1. School of Computer and Control Engineering, Yantai University, Huanghai, Yantai, 264005, Shandong, China

    Yanming Liu & Jinglei Liu

Authors
  1. Yanming Liu
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Jinglei Liu
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Jinglei Liu.

Ethics declarations

Conflict of interest

The authors have no relevant financial or non-financial interests to disclose. The authors have no conflicts of interest to declare that are relevant to the content of this article. There are no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript. The authors have no financial or proprietary interests in any material discussed in this article.

Additional information

Publisher's Note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, Y., Liu, J. Leveraging self-paced learning and deep sparse embedding for image clustering. Neural Comput & Applic 36, 5135–5151 (2024). https://doi.org/10.1007/s00521-023-09335-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-023-09335-w

Keywords