Deep Multiview Clustering by Contrasting Cluster Assignments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Jie, Mao, Hua, Woo, Wai Lok, Peng, Xi
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910309090852864
author Chen, Jie
Mao, Hua
Woo, Wai Lok
Peng, Xi
author_facet Chen, Jie
Mao, Hua
Woo, Wai Lok
Peng, Xi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2304_10769
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Deep Multiview Clustering by Contrasting Cluster Assignments
Chen, Jie
Mao, Hua
Woo, Wai Lok
Peng, Xi
Computer Vision and Pattern Recognition
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.
title Deep Multiview Clustering by Contrasting Cluster Assignments
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2304.10769