Skip to main content
SpringerLink
Log in

Deep boundary-aware clustering by jointly optimizing unsupervised representation learning

  • 1168: Deep Pattern Discovery for Big Multimedia Data
  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Deep clustering obtains feature representation generally and then performs clustering for high dimension real-world data. However, conventional solutions are two-stage embedding learning-based methods and these two processes are separate and independent, which often leads to clustering results cannot feedback to optimize the representation learning and reduces the performance of deep clustering. In this paper, we aim to propose a deep boundary-aware clustering by jointly optimizing unsupervised representation learning. More specifically, we joint boundary-aware variational auto-encoder and deep regularized clustering for deep regularized clustering for unsupervised learning, named Boundary-aware DEep Clustering (BaDEC). BaDEC is able to learn feature representation and clustering simultaneously, and it introduces deep regularized clustering to reduce the unreliability of the similarity measures. In particular, we present a boundary-aware variational auto-encoder that tunes variable evidence lower bounds flexibly to assist feature representation learning better for more accurate clustering. Extensive experiments on various datasets from multiple domains demonstrate that the proposed method outperforms several popular comparison baseline methods.

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

Similar content being viewed by others

Notes

  1. http://yann.lecun.com/exdb/mnist/

  2. https://github.com/zalandoresearch/fashion-mnist

  3. http://qwone.com/jason/20Newsgroups/

  4. https://github.com/philipperemy/Reuters-full-data-set

References

  1. Boutsidis C, Drineas P, Mahoney MW (2009) Unsupervised feature selection for the \(k\)-means clustering problem. In: Advances in neural information processing systems, pp. 153–161

  2. Chen X, Kingma DP, Salimans T, Duan Y, Dhariwal P, Schulman J, Sutskever I, Abbeel P (2017) Variational lossy autoencoder. In: 5th international conference on learning representations, Toulon, France, April 24-26

  3. Devlin J, Chang MW, Lee K, Toutanova K Bert (2019) Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 conference of the north american chapter of the association for computational linguistics: human language technologies, Minneapolis, MN, USA, June 2-7, pp. 4171–4186

  4. Fu Y, Yan Q, Liao J, Xiao C (2020) Joint texture and geometry optimization for RGB-D reconstruction. In: 2020 IEEE/CVF conference on computer vision and pattern recognition, Seattle, WA, USA, June 13-19, pp. 5949–5958

  5. 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

  6. Gregor K, Besse F, Rezende DJ, Danihelka I, Wierstra, D (2016) Towards conceptual compression. In: Advances in neural information processing systems 29: Annual conference on neural information processing systems, Barcelona, Spain, December 5-10, pp. 3549–3557

  7. Guo X, Gao L, Liu X, Yin J (2017) Improved deep embedded clustering with local structure preservation. In: IJCAI, pp. 1753–1759

  8. Huang C, Sankaran K, Dhekane E, Lacoste A, Courville AC (2019) Hierarchical importance weighted autoencoders. In: Proceedings of the 36th international conference on machine learning, Long Beach, California, USA, June 9-15, pp. 2869–2878

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

  10. Jiang B, Tu W, Yang C, Yuan J (2020) Context-integrated and feature-refined network for lightweight object parsing. IEEE Trans Image Process 29:5079–5093

    Article  Google Scholar 

  11. 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 twenty-sixth international joint conference on artificial intelligence, pp. 1965–1972

  12. Kingma DP, Welling M (2014) Auto-encoding variational bayes. In: 2nd international conference on learning representations

  13. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp. 1097–1105

  14. Liu D, Long C, Zhang H, Yu H, Dong X, Xiao C (2020) Arshadowgan: Shadow generative adversarial network for augmented reality in single light scenes. In: 2020 IEEE/CVF conference on computer vision and pattern recognition, Seattle, WA, USA, June 13-19, pp. 8136–8145

  15. Martínez-Trinidad JF, Ruiz-Shulcloper J (2001) Fuzzy clustering of semantic spaces. Pattern Recognition 34(4):783–793

    Article  Google Scholar 

  16. Mukherjee S, Asnani H, Lin E, Kannan S (2019) Clustergan: Latent space clustering in generative adversarial networks. In: Proceedings of the thirty-third AAAI conference on artificial intelligence, pp. 1181–1190

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

  18. Rainforth T, Kosiorek AR, Le TA, Maddison CJ, Igl M, Wood F, Teh YW (2018) Tighter variational bounds are not necessarily better. In: Proceedings of the 35th international conference on machine learning, pp. 4274–4282

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

    Article  Google Scholar 

  20. Solorio-Fernández S, Martínez-Trinidad JF, Carrasco-Ochoa JA (2017) A new unsupervised spectral feature selection method for mixed data: a filter approach. Pattern Recognition 72:314–326

    Article  Google Scholar 

  21. Vincent P, Larochelle H, Lajoie I, Bengio Y, Manzagol PA (2010) Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research 11:3371–3408

    MathSciNet  MATH  Google Scholar 

  22. Xiang S, Nie F, Zhang C (2008) Learning a mahalanobis distance metric for data clustering and classification. Pattern recognition 41(12):3600–3612

    Article  Google Scholar 

  23. Xiao H, Rasul K, Vollgraf R (2017) Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv:1708.07747

  24. Xie J, Girshick R, Farhadi A (2016) Unsupervised deep embedding for clustering analysis. In: International conference on machine learning, pp. 478–487

  25. Xing EP, Jordan MI, Russell, SJ, Ng AY (2003) Distance metric learning with application to clustering with side-information. In: Advances in neural information processing systems, pp. 521–528

  26. Yang J, Parikh D, Batra D (2016) Joint unsupervised learning of deep representations and image clusters. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5147–5156

  27. Ye J, Zhao Z, Wu M (2008) Discriminative k-means for clustering. In: Advances in neural information processing systems, pp. 1649–1656

  28. Yu J, Jiang H, Wang G, Guo Q (2012) Clustering-based energy-efficient broadcast tree in wireless networks. Int. J. Comput. Commun. Control 7(4):785–790

    Article  Google Scholar 

  29. Zhang R, Tong H, Xia Y, Zhu Y (2019) Robust embedded deep k-means clustering. In: Proceedings of the 28th international conference on information and knowledge management, Beijing, China, November 3-7, pp. 1181–1190

  30. Zhou F, De la Torre F, Hodgins JK (2012) Hierarchical aligned cluster analysis for temporal clustering of human motion. IEEE Transactions on Pattern Analysis and Machine Intelligence 35(3):582–596

    Article  Google Scholar 

Download references

Acknowledgements

This work is supported by the National Natural Science Foundation of China (Grant No. 61602353 and 61373148), Hubei Provincial Natural Science Foundation of China (Grant No. 2017CFA012), the National Social Science Foundation under Award (Grant No. 19BYY076), in part Key R & D project of Shandong Province (Grant No. 2019JZZY010129), and Shandong Provincial Social Science Planning Project (Grant No. 18CXWJ01, 18BJYJ04 and 19BJCJ51).

Author information

Authors and Affiliations

  1. School of Information Science and Engineering, Shandong Normal University, Jinan, China

    Ru Wang & Peiyu Liu

  2. School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China

    Lin Li & Peipei Wang

  3. School of Sciences, University of Southern Queensland, Toowoomba, Australia

    Xiaohui Tao

Authors
  1. Ru Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lin Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Peipei Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xiaohui Tao
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Peiyu Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Lin Li or Peiyu Liu.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, R., Li, L., Wang, P. et al. Deep boundary-aware clustering by jointly optimizing unsupervised representation learning. Multimed Tools Appl 81, 34309–34324 (2022). https://doi.org/10.1007/s11042-021-11597-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-021-11597-2

Keywords

Search

Navigation