Abstract
Correlation Clustering, also called the minimum cost Multicut problem, is the process of grouping data by pairwise similarities. It has proven to be effective on clustering problems, where the number of classes is unknown. However, not only is the Multicut problem NP-hard, an undirected graph G with n vertices representing single images has at most \(\frac{n(n-1)}{2}\) edges, thus making it challenging to implement correlation clustering for large datasets. In this work, we propose Multi-Stage Multicuts (MSM) as a scalable approach for image clustering. Specifically, we solve minimum cost Multicut problems across multiple distributed compute units. Our approach not only allows to solve problem instances which are too large to fit into the shared memory of a single compute node, but it also achieves significant speedups while preserving the clustering accuracy at the same time. We evaluate our proposed method on the CIFAR10 and CelebA image datasets. Furthermore, we also provide the proof for the theoretical speedup.
K. Ho and A. Chatzimichailidis—Equal contribution.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Beier, T., Kroeger, T., Kappes, J.H., Kothe, U., Hamprecht, F.A.: Cut, glue & cut: a fast, approximate solver for multicut partitioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 73–80 (2014)
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)
Caron, M., Bojanowski, P., Mairal, J., Joulin, A.: Unsupervised pre-training of image features on non-curated data. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2959–2968 (2019)
Caron, M., et al.: Emerging properties in self-supervised vision transformers. arXiv preprint arXiv:2104.14294 (2021)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597–1607. PMLR (2020)
Chopra, S., Rao, M.R.: The partition problem. Math. Program. 59(1–3), 87–115 (1993). https://doi.org/10.1007/BF01581239
Dean, J., et al.: Large scale distributed deep networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1223–1231. Curran Associates Inc. (2012)
Demaine, E.D., Emanuel, D., Fiat, A., Immorlica, N.: Correlation clustering in general weighted graphs. Theor. Comput. Sci. 361(2–3), 172–187 (2006)
Ghasedi, K., Wang, X., Deng, C., Huang, H.: Balanced self-paced learning for generative adversarial clustering network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4391–4400 (2019)
Ghasedi Dizaji, K., Herandi, A., Deng, C., Cai, W., Huang, H.: Deep clustering via joint convolutional autoencoder embedding and relative entropy minimization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5736–5745 (2017)
Guo, S., Xu, J., Chen, D., Zhang, C., Wang, X., Zhao, R.: Density-aware feature embedding for face clustering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6698–6706 (2020)
Harlap, A., et al.: PipeDream: fast and efficient pipeline parallel DNN training. CoRR arXiv:1806.03377 (2018)
Ho, K., Keuper, J., Pfreundt, F., Keuper, M.: Learning embeddings for image clustering: an empirical study of triplet loss approaches. arXiv preprint arXiv:2007.03123 (2020)
Huang, Y., et al.: GPipe: efficient training of giant neural networks using pipeline parallelism. CoRR arXiv:1811.06965 (2018)
Kardoost, A., Ho, K., Ochs, P., Keuper, M.: Self-supervised sparse to dense motion segmentation. In: Proceedings of the Asian Conference on Computer Vision (2020)
Kernighan, B.W., Lin, S.: An efficient heuristic procedure for partitioning graphs. Bell Syst. Tech. J. 49(2), 291–307 (1970)
Keuper, M., Tang, S., Andres, B., Brox, T., Schiele, B.: Motion segmentation & multiple object tracking by correlation co-clustering. IEEE Trans. Pattern Anal. Mach. Intell. 42(1), 140–153 (2018)
Kolesnikov, A., et al.: Big transfer (bit): general visual representation learning, vol. 6, no. 2, p. 8. arXiv preprint arXiv:1912.11370 (2019)
Krizhevsky, A.: One weird trick for parallelizing convolutional neural networks. CoRR arXiv:1404.5997 (2014)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. Technical report, Citeseer (2009)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105 (2012)
Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logist. (NRL) 52(1), 7–21 (2005)
Li, P., Zhao, H., Liu, H.: Deep fair clustering for visual learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9070–9079 (2020)
Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of International Conference on Computer Vision (ICCV), December 2015
Mukherjee, S., Asnani, H., Lin, E., Kannan, S.: ClusterGAN: latent space clustering in generative adversarial networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 4610–4617 (2019)
Pan, X., Papailiopoulos, D., Oymak, S., Recht, B., Ramchandran, K., Jordan, M.I.: Parallel correlation clustering on big graphs. arXiv preprint arXiv:1507.05086 (2015)
Pishchulin, L., et al.: DeepCut: joint subset partition and labeling for multi person pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4929–4937 (2016)
Tang, S., Andres, B., Andriluka, M., Schiele, B.: Multi-person tracking by multicut and deep matching. CoRR arXiv:1608.05404 (2016)
Wolf, S., et al.: The mutex watershed and its objective: efficient, parameter-free graph partitioning. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3724–3738 (2020)
Xie, J., Girshick, R., Farhadi, A.: Unsupervised deep embedding for clustering analysis. In: International Conference on Machine Learning, pp. 478–487. PMLR (2016)
Zhan, X., Xie, J., Liu, Z., Ong, Y., Loy, C.C.: Online deep clustering for unsupervised representation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6688–6697 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Ho, K., Chatzimichailidis, A., Keuper, M., Keuper, J. (2021). MSM: Multi-stage Multicuts for Scalable Image Clustering. In: Jagode, H., Anzt, H., Ltaief, H., Luszczek, P. (eds) High Performance Computing. ISC High Performance 2021. Lecture Notes in Computer Science(), vol 12761. Springer, Cham. https://doi.org/10.1007/978-3-030-90539-2_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-90539-2_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-90538-5
Online ISBN: 978-3-030-90539-2
eBook Packages: Computer ScienceComputer Science (R0)