论文丨J. Chen, H. Mao, W. L. Woo, and X. Peng*：Deep multiview clustering by contrasting cluster assignments

本文（Deep multiview clustering by contrasting cluster assignments ）原载IEEE/CVF International Conference on Computer Vision (ICCV)，由四川大学陈杰副教授等科研人员创作，系四川大学智慧法治超前部署学科系列学术成果。后续会持续分享四川大学智慧法治超前部署学科系列学术成果，欢迎大家阅读。

Abstract:Multiview clustering (MVC) aims to reveal the underlying structure of multiview data by categorizing data samples into clusters. Deep learning-based methods exhibit strong feature learning capabilities on large-scale datasets. For most existing deep MVC methods, exploring the invariant representations of multiple views is still an intractable problem. In this paper, we propose a cross-view contrastive learning (CVCL) method that learns view-invariant representations and produces clustering results by contrasting the cluster assignments among multiple views. Specifically, we first employ deep autoencoders to extract view-dependent features in the pretraining stage. Then, a cluster-level CVCL strategy is presented to explore consistent semantic label information among the multiple views in the fine-tuning stage. Thus, the proposed CVCL method is able to produce more discriminative cluster assignments by virtue of this learning strategy. Moreover, we provide a theoretical analysis of soft cluster assignment alignment. Extensive experimental results obtained on several datasets demonstrate that the proposed CVCL method outperforms several state-of-the-art approaches.

J. Chen, H. Mao, W. L. Woo, and X. Peng*. “Deep multiview clustering by contrasting cluster assignments”, Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 16752-16761, Paris, France, Oct. 4-6, 2023.（论文下载）