Deep Mutual Information Decoupling based Unsupervised Image Clustering

Yanfeng  Wang; Jinfeng  Wang; Weirong  Zhang

doi:10.6180/jase.202506_28(6).0014

Deep Mutual Information Decoupling based Unsupervised Image Clustering

Electrical Engineering Mechanical Engineering

Yanfeng Wang¹, Jinfeng Wang², and Weirong Zhang²This email address is being protected from spambots. You need JavaScript enabled to view it.

¹School of Mechanical and Electrical Engineering, Weifang Vocational College, Weifang, 262737, China

²School of Information Engineering, Weifang Vocational College, Weifang, 262737, China

Received: July 14, 2024
Accepted: August 24, 2024
Publication Date: September 11, 2024

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202506_28(6).0014

Cross-view image clustering (CIC) showcases immense potential in recognizing image patterns due to the power to aggregate information between views without labels. However, most CIC ignore intricate coupling relationships between category and redundant features in aggregating complementary information of cross-view images, which may restrict performance in recognizing patterns of images. To this end, a cross-view mutual information decoupling based deep generative clustering approach is proposed for recognizing image patterns (DMID-UIC), which contains information maximization deep generative module and self-supervised posterior inference module. Specifically, the former maximizes the mutual information between data and semantics within the generative adversarial network to decouple category and redundant features hidden in cross-view images, which guarantees the separation of different semantic distributions in the data space. The latter models the distribution fitting between generated data and the prior semantic code as a classification task, via treating partitioning results of common representations between views as self-supervised labels. Meanwhile, to better optimize the model, an EM optimization strategy is designed to enhance the above two module learning in an iterative manner. Finally, comprehensive results verify the superiority and effectiveness of DMID-UIC. DMID-UIC improves ACC by 10.1% on the Caltech 101-7 dataset, compared to the second-best result.

Keywords: Unsupervised image clustering; mutual information decoupling; deep cross-view learning

[1] K. Cui, R. Li, S. L. Polk, Y. Lin, H. Zhang, J. M. Murphy, R. J. Plemmons, and R. H. Chan, (2024) “Superpixel-based and Spatially-regularized Diffusion Learning for Unsupervised Hyperspectral Image Clustering" IEEE Transactions on Geoscience and Remote Sensing: DOI: 10.1109/TGRS.2024.3385202.
[2] H. Huang, C. Wang, X. Wei, and Y. Zhou, (2024) “Deep Image Clustering: A survey" Neurocomputing: 128101. DOI: 10.1016/j.neucom.2024.128101.
[3] P. Li, J. Gao, J. Zhang, S. Jin, and Z. Chen, (2022) “Deep Reinforcement Clustering" IEEE Transactions on Multimedia 25: 8183–8193. DOI: 10.1109/TMM.2022. 3233249.
[4] J. Gao, M. Liu, P. Li, J. Zhang, and Z. Chen, (2023) “Deep Multiview Adaptive Clustering With Semantic Invariance" IEEE Transactions on Neural Networks and Learning Systems: DOI: 10.1109/TMM.2022.3233249.
[5] P. Li, Z. Chen, L. T. Yang, J. Gao, Q. Zhang, and M. J. Deen, (2018) “An incremental deep convolutional computation model for feature learning on industrial big data" IEEE Transactions on Industrial Informatics 15(3): 1341–1349. DOI: 10.1109/TII.2018.2871084.
[6] C. Cui, Y. Ren, J. Pu, J. Li, X. Pu, T. Wu, Y. Shi, and L. He, (2024) “A novel approach for effective multi-view clustering with information-theoretic perspective" Advances in Neural Information Processing Systems 36:
[7] Q. Xiao, J. Dai, J. Luo, and H. Fujita, (2019) “Multiview manifold regularized learning-based method for prioritizing candidate disease miRNAs" Knowledge-Based Systems 175: 118–129. DOI: 10.1016/j.knosys.2019.03.023.
[8] G. Andrew, R. Arora, J. Bilmes, and K. Livescu. “Deep canonical correlation analysis”. In: International conference on machine learning. 2013, 1247–1255.
[9] C. Zhang, Y. Liu, and H. Fu. “Ae2-nets: Autoencoder in autoencoder networks”. In: computer vision and pattern recognition. 2019, 2577–2585. DOI: 10.1109/CVPR.2019.00268.
[10] Z. Wan, C. Zhang, P. Zhu, and Q. Hu. “Multi-view information-bottleneck representation learning”. In: AAAI conference on artificial intelligence. 35. 11. 2021, 10085–10092. DOI: 10.1609/aaai.v35i11.17210.
[11] Q. Gao, H. Lian, Q. Wang, and G. Sun. “Cross-modal subspace clustering via deep canonical correlation analysis”. In: AAAI Conference on artificial intelligence. 34. 04. 2020, 3938–3945. DOI: 10.1609/aaai.v34i04.5808.
[12] M. Yang, Y. Li, P. Hu, J. Bai, J. Lv, and X. Peng, (2022) “Robust multi-view clustering with incomplete information" IEEE Transactions on Pattern Analysis and Machine Intelligence 45(1): 1055–1069. DOI: 10.1109/TPAMI.2022.3155499.
[13] C. Cui, Y. Ren, J. Pu, X. Pu, and L. He. “Deep multiview subspace clustering with anchor graph”. In: International Joint Conference on Artificial Intelligence. 2023, 3577–3585. DOI: 10.48550/arXiv.2305.06939.
[14] Z. Gu and S. Feng, (2023) “Individuality meets commonality: A unified graph learning framework for multi-view clustering" ACM Transactions on Knowledge Discovery from Data 17(1): 1–21. DOI: 10.1145/3532612.
[15] D. J. Trosten, S. Lokse, R. Jenssen, and M. Kampffmeyer. “Reconsidering representation alignment for multi-view clustering”. In: computer vision and pattern recognition. 2021, 1255–1265. DOI: 10.1109/CVPR46437.2021.0013.
[16] J. Xu, Y. Ren, H. Tang, Z. Yang, L. Pan, Y. Yang, X. Pu, S. Y. Philip, and L. He, (2022) “Self-supervised discriminative feature learning for deep multi-view clustering" IEEE Transactions on Knowledge and Data Engineering 35(7): 7470–7482. DOI: 10.1109/TKDE.2022.3193569.
[17] R. Zhou and Y.-D. Shen. “End-to-end adversarialattention network for multi-modal clustering”. In: computer vision and pattern recognition. 2020, 14619– 14628.
[18] J. Xu, C. Li, Y. Ren, L. Peng, Y. Mo, X. Shi, and X. Zhu. “Deep incomplete multi-view clustering via mining cluster complementarity”. In: conference on artificial intelligence. 36. 8. 2022, 8761–8769. DOI: 10.1609/aaai.v36i8.20856.
[19] X. Yang, J. Jiaqi, S. Wang, K. Liang, Y. Liu, Y. Wen, S. Liu, S. Zhou, X. Liu, and E. Zhu. “Dealmvc: Dual contrastive calibration for multi-view clustering”. In: ACM International Conference on Multimedia. 2023, 337–346. DOI: 10.1145/3581783.361195.
[20] Y. Ling, J. Chen, Y. Ren, X. Pu, J. Xu, X. Zhu, and L. He. “Dual label-guided graph refinement for multi-view graph clustering”. In: AAAI Conference on Artificial Intelligence. 37. 7. 2023, 8791–8798. DOI: 10.1609/aaai.v37i7.26057.
[21] J. Wen, C. Liu, G. Xu, Z. Wu, C. Huang, L. Fei, and Y. Xu. “Highly confident local structure based consensus graph learning for incomplete multi-view clustering”. In: Computer Vision and Pattern Recognition. 2023, 15712–15721.