Multi-View Deep Clustering based on AutoEncoder

In recent years, with the development of deep learning, replacing traditional clustering methods with subspaces extracted by deep neural networks will help better clustering performance. However, due to the instability of unsupervised learning, the features extracted each time are different even if...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series Vol. 1684; no. 1; pp. 12059 - 12066
Main Authors: Dong, Shihao, Xu, Huiying, Zhu, Xinzhong, Guo, XiFeng, Liu, Xinwang, Wang, Xia
Format: Journal Article
Language:English
Published: IOP Publishing 01.11.2020
ISSN:1742-6588, 1742-6596
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In recent years, with the development of deep learning, replacing traditional clustering methods with subspaces extracted by deep neural networks will help better clustering performance. However, due to the instability of unsupervised learning, the features extracted each time are different even if the same data is processed. In order to improve the stability and performance of clustering, we propose a novel unsupervised deep embedding clustering multi-view method, which treats multiple different subspaces as different views through some data expansion methods for the same data. Specifically, our method uses a variety of different deep autoencoders to learn the latent representation of the original data and constrain them to learn different features. Our experimental evaluations on several natural image datasets show that this method has a significant improvement compared to existing methods.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1684/1/012059