Deep Image Clustering Based on Label Similarity and Maximizing Mutual Information across Views
Source abstract
Abstract
Most existing deep image clustering methods use only class-level representations for clustering. However, the class-level representation alone is not sufficient to describe the differences between images belonging to the same cluster. This may lead to high intra-class representation differences, which will harm the clustering performance. To address this problem, this paper proposes a clustering model named Deep Image Clustering based on Label Similarity and Maximizing Mutual Information Across Views (DCSM). DCSM consists of a backbone network, class-level and instance-level mapping block. The class-level mapping block learns discriminative class-level features by selecting similar (dissimilar) pairs of samples. The proposed extended mutual information is to maximize the mutual information between features extracted from views that were obtained by using data augmentation on the same image and as a constraint on the instance-level mapping block. This forces the instance-level mapping block to capture high-level features that affect multiple views of the same image, thus reducing intra-class differences. Four representative datasets are selected for our experiments, and the results show that the proposed model is superior to the current advanced image clustering models.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Image Retrieval and Classification Techniques · Advanced Image and Video Retrieval Techniques · Remote-Sensing Image Classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Cyber Security and Computer, Hebei University, Baoding 071000, China
Hebei Machine Vision Engineering Research Center, Baoding 071000, China
Funding
Natural Science Foundation of Hebei Province · Hebei University High-level Scientific Research Foundation for the Introduction of Talent · Post-graduate’s Innovation Fund Project of Hebei University
References (45)
Show source-provided references
1. Deep clustering by maximizing mutual information in variational auto-encoder10.1016/j.knosys.2020.106260 ↗
2. Contrastive Author-aware Text Clustering10.1016/j.patcog.2022.108787 ↗
3. Tensorial Multi-view Clustering via Low-rank Constrained High-order Graph Learning10.1109/TCSVT.2022.3143848 ↗
4. Towards Adaptive Consensus Graph: Multi-view Clustering via Graph Collaboration
5. MacQueen, J. (July, January 21). Some methods for classification and analysis of multivariate observations. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Los Angeles, CA, USA.
6. A tutorial on spectral clustering10.1007/s11222-007-9033-z ↗
7. Clustering by fast search and find of density peaks10.1126/science.1242072 ↗
8. Image quality measures based on intuitionistic fuzzy similarity and inclusion measures10.3233/JIFS-171480 ↗
9. Low-rank sparse subspace for spectral clustering
10. Kernelized multiview subspace analysis by self-weighted learning10.1109/TMM.2020.3032023 ↗
11. Ding, X., Zhang, X., Ma, N., Jun, H., Gui, D., and Jian, S. (2021, January 20–25). Repvgg: Making vgg-style convnets great again. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01352 ↗
12. Kaur, P., Harnal, S., Tiwari, R., Alharithi, F.S., Almulihi, A.H., Noya, I.D., and Goyal, N. (2021). A hybrid convolutional neural network model for diagnosis of COVID-19 using chest X-ray images. Int. J. Environ. Res. Public Health, 18.10.3390/ijerph182212191 ↗
13. Discriminative feature and dictionary learning with part-aware model for vehicle re-identification10.1016/j.neucom.2020.06.148 ↗
14. Multi-path deep cnns for fine-grained car recognition10.1109/TVT.2020.3009162 ↗
15. Attribute-guided feature learning network for vehicle reidentification10.1109/MMUL.2020.2999464 ↗
16. Chugh, H., Gupta, S., Garg, M., Gupta, D., Mohamed, H.G., Noya, I.D., Singh, A., and Goyal, N. (2022). An Image Retrieval Framework Design Analysis Using Saliency Structure and Color Difference Histogram. Sustainability, 14.10.3390/su141610357 ↗
17. A survey of clustering with deep learning: From the perspective of network architecture10.1109/ACCESS.2018.2855437 ↗
18. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
19. Reducing the dimensionality of data with neural networks10.1126/science.1127647 ↗
20. Kingma, D.P., and Welling, M. (2013). Auto-encoding variational bayes. arXiv.
21. Generative adversarial networks10.1145/3422622 ↗
22. Yu, Y., and Zhou, W. (2018, January 13–19). Mixture of GANs for clustering. Proceedings of the 27th International Joint Conference on Artificial Intelligence, Stockholm, Sweden.
23. Ghasedi, K., Wang, X., Deng, C., and Huang, H. (2019, January 16–17). Balanced self-paced learning for generative adversarial clustering network. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00452 ↗
24. Mukherjee, S., Asnani, H., Lin, E., and Kannan, S. (March, January 22). Clustergan: Latent space clustering in generative adversarial networks. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA.
25. Unsupervised discriminative feature learning via finding a clustering-friendly embedding space10.1016/j.patcog.2022.108768 ↗
26. Chang, J., Wang, L., Meng, G., Xiang, S., and Pan, C. (2017, January 22–29). Deep adaptive image clustering. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.626 ↗
27. Wu, J., Long, K., Wang, F., Qian, C., Li, C., Lin, Z., and Zha, H. (2019, January 27–28). Deep comprehensive correlation mining for image clustering. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.10.1109/ICCV.2019.00824 ↗
28. Xu, J., Henriques, J.F., and Vedaldi, A. (2019, January 27–28). Invariant information clustering for unsupervised image classification and segmentation. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
29. Yang, B., Fu, X., Sidiropoulos, N.D., and Hong, M. (2017, January 6–11). Towards k-means-friendly spaces: Simultaneous deep learning and clustering. Proceedings of the International Conference on Machine Learning, PMLR, Sydney, Australia.
30. Deep k-means: Jointly clustering with k-means and learning representations10.1016/j.patrec.2020.07.028 ↗
31. Pseudo-supervised deep subspace clustering10.1109/TIP.2021.3079800 ↗
32. Deep embedding clustering based on contractive autoencoder10.1016/j.neucom.2020.12.094 ↗
33. Deep density-based image clustering10.1016/j.knosys.2020.105841 ↗
34. Yang, J., Parikh, D., and Batra, D. (2016, January 27–30). Joint unsupervised learning of deep representations and image clusters. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.556 ↗
35. Active deep image clustering10.1016/j.knosys.2022.109346 ↗
36. Image clustering using an augmented generative adversarial network and information maximization10.1109/TNNLS.2021.3085125 ↗
37. Xie, J., Girshick, R., and Farhadi, A. (2016, January 20–22). Unsupervised deep embedding for clustering analysis. Proceedings of the International Conference on Machine Learning, New York, NY, USA.
38. Van Gansbeke, W., Vandenhende, S., Georgoulis, S., Proesmans, M., and Van Gool, L. (2020, January 23–28). Scan: Learning to classify images without labels. Proceedings of the European Conference on Computer Vision, Glasgow, UK.10.1007/978-3-030-58607-2_16 ↗
39. Belghazi, M.I., Baratin, A., Rajeshwar, S., Ozair, S., Bengio, Y., Courville, A., and Hjelm, D. (2018, January 10–15). Mutual information neural estimation. Proceedings of the International Conference on Machine Learning, PMLR, Stockholm, Sweden.
40. Hjelm, R.D., Fedorov, A., Lavoie-Marchildon, S., Grewal, K., Bachman, P., Trischler, A., and Bengio, Y. (2018). Learning deep representations by mutual information estimation and maximization. arXiv.
41. Discriminative clustering by regularized information maximization
42. Hu, W., Miyato, T., Tokui, S., Matsumoto, E., and Sugiyama, M. (2017, January 6–11). Learning discrete representations via information maximizing self-augmented training. Proceedings of the International Conference on Machine Learning, PMLR, Sydney, Australia.
43. f-gan: Training generative neural samplers using variational divergence minimization
44. Niu, C., Zhang, J., Wang, G., and Liang, J. (2020, January 23–28). Gatcluster: Self-supervised gaussian-attention network for image clustering. Proceedings of the European Conference on Computer Vision, Glasgow, UK.10.1007/978-3-030-58595-2_44 ↗
45. Kingma, D.P., and Ba, J. (2015, January 7–9). Adam: A method for stochastic optimization. Proceedings of the International Conference on Learning Representations (ICLR), San Diego, CA, USA.