Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
173 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Decoupled Contrastive Multi-View Clustering with High-Order Random Walks (2308.11164v2)

Published 22 Aug 2023 in cs.CV

Abstract: In recent, some robust contrastive multi-view clustering (MvC) methods have been proposed, which construct data pairs from neighborhoods to alleviate the false negative issue, i.e., some intra-cluster samples are wrongly treated as negative pairs. Although promising performance has been achieved by these methods, the false negative issue is still far from addressed and the false positive issue emerges because all in- and out-of-neighborhood samples are simply treated as positive and negative, respectively. To address the issues, we propose a novel robust method, dubbed decoupled contrastive multi-view clustering with high-order random walks (DIVIDE). In brief, DIVIDE leverages random walks to progressively identify data pairs in a global instead of local manner. As a result, DIVIDE could identify in-neighborhood negatives and out-of-neighborhood positives. Moreover, DIVIDE embraces a novel MvC architecture to perform inter- and intra-view contrastive learning in different embedding spaces, thus boosting clustering performance and embracing the robustness against missing views. To verify the efficacy of DIVIDE, we carry out extensive experiments on four benchmark datasets comparing with nine state-of-the-art MvC methods in both complete and incomplete MvC settings.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. Learning from multiple partially observed views-an application to multilingual text categorization. Advances in neural information processing systems, 22.
  2. A Simple Framework for Contrastive Learning of Visual Representations. In Proc. Int. Conf. Mach. Learn., 1597–1607.
  3. An Empirical Study of Training Self-Supervised Vision Transformers. arXiv preprint arXiv:2104.02057.
  4. Debiased contrastive learning. Advances in neural information processing systems, 33: 8765–8775.
  5. Fang, S. 2023. Incomplete Multi-view Clustering via Diffusion Completion. arXiv preprint arXiv:2305.11489.
  6. Trusted Multi-View Classification. In Proc. Int. Conf. Learn. Representations.
  7. Momentum Contrast for Unsupervised Visual Representation Learning. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 9726–9735.
  8. Doubly Aligned Incomplete Multi-view Clustering. In Proc. Int. Joint Conf. Artif. Intell., 2262–2268.
  9. Multi-view Spectral Clustering Network. In Proc. Int. Joint Conf. Artif. Intell., 2563–2569.
  10. Boosting contrastive self-supervised learning with false negative cancellation. In Proceedings of the IEEE/CVF winter conference on applications of computer vision, 2785–2795.
  11. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning, 448–456. pmlr.
  12. DM2C: Deep Mixed-Modal Clustering. In Proc. Int. Conf. Neural Inf. Process. Syst., 5880–5890.
  13. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25.
  14. A bayesian hierarchical model for learning natural scene categories. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 524–531.
  15. Incomplete Multi-view Clustering via Prototype-based Imputation. arXiv preprint arXiv:2301.11045.
  16. Partial multi-view clustering. In Proceedings of the AAAI conference on artificial intelligence, volume 28.
  17. Large-Scale Multi-View Spectral Clustering via Bipartite Graph. In Proc. AAAI Conf. Artif. Intell., 2750–2756.
  18. Contrastive multi-view hyperbolic hierarchical clustering. arXiv preprint arXiv:2205.02618.
  19. Dual contrastive prediction for incomplete multi-view representation learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4): 4447–4461.
  20. COMPLETER: Incomplete Multi-view Clustering via Contrastive Prediction. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 11174–11183.
  21. Graph Matching with Bi-level Noisy Correspondence. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV).
  22. Improve Interpretability of Neural Networks via Sparse Contrastive Coding. In Findings of the Association for Computational Linguistics: EMNLP 2022.
  23. Efficient and Effective Regularized Incomplete Multi-view Clustering. IEEE Trans. Pattern Anal. Mach. Intell., 43(8): 2634–2646.
  24. Lovász, L. 1993. Random walks on graphs. Combinatorics, Paul erdos is eighty, 2(1-46): 4.
  25. Visualizing data using t-SNE. J. Mach. Learn. Res., 9(Nov): 2579–2605.
  26. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
  27. Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 6420–6429.
  28. Deep safe incomplete multi-view clustering: Theorem and algorithm. In International Conference on Machine Learning, 21090–21110. PMLR.
  29. Reconsidering representation alignment for multi-view clustering. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 1255–1265.
  30. On the Effects of Self-supervision and Contrastive Alignment in Deep Multi-view Clustering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 23976–23985.
  31. Self-supervised learning from a multi-view perspective. In ICLR.
  32. Rethinking minimal sufficient representation in contrastive learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 16041–16050.
  33. On Deep Multi-View Representation Learning. In Proc. Int. Conf. Mach. Learn., 1083–1092.
  34. Adversarial incomplete multi-view clustering. In IJCAI, volume 7, 3933–3939.
  35. A review of multimodal human activity recognition with special emphasis on classification, applications, challenges and future directions. Knowledge-Based Systems, 223: 106970.
  36. Learning with Twin Noisy Labels for Visible-Infrared Person Re-Identification. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit.
  37. Robust Multi-view Clustering with Incomplete Information. IEEE Trans. Pattern Anal. Mach. Intell.
  38. Bag-of-visual-words and spatial extensions for land-use classification. In Proc. ACM SIGSPATIAL Int. Conf. Adv. Inf., 270–279.
  39. Deep Partial Multi-View Learning. IEEE Trans. Pattern Anal. Mach. Intell.
  40. CPM-Nets: Cross Partial Multi-View Networks. In Proc. Int. Conf. Neural Inf. Process. Syst., 557–567.
  41. AE2-Nets: Autoencoder in Autoencoder Networks. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2577–2585.
  42. Binary Multi-View Clustering. IEEE Trans. Pattern Anal. Mach. Intell., 41(7): 1774–1782.
  43. Contrastive learning with complex heterogeneity. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2594–2604.
  44. Graph Contrastive Clustering. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 9224–9233.
  45. Crossclr: Cross-modal contrastive learning for multi-modal video representations. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 1450–1459.
Citations (21)

Summary

We haven't generated a summary for this paper yet.