Abstract
Deep Multi-task image clustering endeavors to leverage deep learning techniques for the simultaneous processing of multiple clustering tasks. Current multi-task deep image clustering approaches typically rely on conventional deep convolutional neural networks and transfer learning technologies. However, suboptimal clustering results are produced in the execution of each task including irrelevant redundant information. This paper proposes a novel end-to-end deep multi-task clustering framework named Deep Multi-Task Image Clustering with Attention-guided Patch Filtering and Correlation Mining (APFMTC) that eliminates redundant information between different tasks while extracting relevant information to achieve improved cluster division. Specifically, APFMTC partitions image samples into several patches, treating each patch as a word thus each image is regarded as an article, and the process of determining the cluster to which an image belongs is likened to categorizing articles. During the clustering process, several parts of each image sample generally carry more significance. Therefore, a weights estimation module is designed to evaluate the importance of different visual words extracted by the key patch filter for different categories. Ultimately, in each task, the final cluster division is determined by assigning weights to the words contained within the image samples. To evaluate the effectiveness of the proposed method, it is tested on multi-task datasets created from four datasets: NUS-Wide, Pascal VOC, Caltech-256, and Cifar-100. The experimental results substantiate the efficacy of the proposed method.
Supported by Central Government Guides Local Science and Technology Development Fund Projects (236Z0301G); Hebei Natural Science Foundation (F2022201009); Science and Technology Project of Hebei Education Department (QN2023186).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Asano, Y., Rupprecht, C., Vedaldi, A.: Self-labelling via simultaneous clustering and representation learning. In: 2020 International Conference on Learning Representations
Cao, W., Wu, S., Yu, Z., Wong, H.S.: Exploring correlations among tasks, clusters, and features for multitask clustering. IEEE Trans. Neural Netw. Learn. Syst. 30(2), 355–368 (2019)
Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 132–149 (2018)
Chefer, H., Gur, S., Wolf, L.: Transformer interpretability beyond attention visualization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 782–791 (2021)
Hu, S., Yan, X., Ye, Y.: Multi-task image clustering through correlation propagation. IEEE Trans. Knowl. Data Eng. 33(03), 1113–1127 (2021)
Ji, X., Henriques, J.F., Vedaldi, A.: Invariant information clustering for unsupervised image classification and segmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision,. pp. 9865–9874 (2019)
Jiang, G., Wang, H., Peng, J., Chen, D., Fu, X.: Graph-based multi-view binary learning for image clustering. Neurocomputing 427, 225–237 (2021)
Park, S., et al.: Improving unsupervised image clustering with robust learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12278–12287 (2021)
Ren, Y., Hu, K., Dai, X., Pan, L., Hoi, S.C., Xu, Z.: Semi-supervised deep embedded clustering. Neurocomputing 325, 121–130 (2019)
Shukla, A., Cheema, G.S., Anand, S.: Semi-supervised clustering with neural networks. In: 2020 IEEE Sixth International Conference on Multimedia Big Data (BigMM), pp. 152–161. IEEE (2020)
Sun, B., Zhou, P., Du, L., Li, X.: Active deep image clustering. Knowl.-Based Syst. 252, 109346 (2022)
Vilhagra, L.A., Fernandes, E.R., Nogueira, B.M.: Textcsn: a semi-supervised approach for text clustering using pairwise constraints and convolutional siamese network. In: Proceedings of the 35th Annual ACM Symposium on Applied Computing, pp. 1135–1142 (2020)
Wang, H., Feng, L., Yu, L., Zhang, J.: Multi-view sparsity preserving projection for dimension reduction. Neurocomputing 216, 286–295 (2016)
Wang, H., Yao, M., Jiang, G., Mi, Z., Fu, X.: Graph-collaborated auto-encoder hashing for multiview binary clustering. IEEE Transactions on Neural Networks and Learning Systems (2023)
Wu, J., et al.: Deep comprehensive correlation mining for image clustering. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8150–8159 (2019)
Xu, C., Lin, R., Cai, J., Wang, S.: Deep image clustering by fusing contrastive learning and neighbor relation mining. Knowl.-Based Syst. 238, 107967 (2022)
Yan, X., Hu, S., Ye, Y.: Multi-task clustering of human actions by sharing information. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6401–6409 (2017)
Yan, X., Mao, Y., Li, M., Ye, Y., Yu, H.: Multitask image clustering via deep information bottleneck. IEEE Transactions on Cybernetics (2023)
Yan, X., Shi, K., Ye, Y., Yu, H.: Deep correlation mining for multi-task image clustering. Expert Syst. Appl. 187, 115973 (2022)
Yan, Y., Ricci, E., Liu, G., Sebe, N.: Egocentric daily activity recognition via multitask clustering. IEEE Trans. Image Process. 24(10), 2984–2995 (2015)
Yang, Y., Ma, Z., Yang, Y., Nie, F., Shen, H.T.: Multitask spectral clustering by exploring intertask correlation. IEEE Trans. Cybern. 45(5), 1069–1080 (2015)
Zhang, H., Zhan, T., Basu, S., Davidson, I.: A framework for deep constrained clustering. Data Min. Knowl. Disc. 35, 593–620 (2021)
Zhang, X.L.: Convex discriminative multitask clustering. IEEE Trans. Pattern Anal. Mach. Intell. 37(01), 28–40 (2015)
Zhang, X., Liu, H., Zhang, X., Liu, X.: Attributed graph clustering with multi-task embedding learning. Neural Netw. 152, 224–233 (2022)
Zhang, X., Zhang, X., Liu, H., Liu, X.: Multi-task multi-view clustering. IEEE Trans. Knowl. Data Eng. 28(12), 3324–3338 (2016)
Zhong, G., Pun, C.M.: Local learning-based multi-task clustering. Knowl.-Based Syst. 255, 109798 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Tian, Z., Li, K., Peng, J. (2024). Deep Multi-task Image Clustering with Attention-Guided Patch Filtering and Correlation Mining. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14428. Springer, Singapore. https://doi.org/10.1007/978-981-99-8462-6_11
Download citation
DOI: https://doi.org/10.1007/978-981-99-8462-6_11
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8461-9
Online ISBN: 978-981-99-8462-6
eBook Packages: Computer ScienceComputer Science (R0)