Open AccessMulti-View Deep Clustering based on AutoEncoder
Author(s) -
Shihao Dong,
Huiying Xu,
Xiaoyan Zhu,
Xifeng Guo,
Xinwang Liu,
Xia Wang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1684/1/012059
Subject(s) - cluster analysis , autoencoder , artificial intelligence , computer science , deep learning , pattern recognition (psychology) , unsupervised learning , linear subspace , embedding , stability (learning theory) , feature learning , clustering high dimensional data , artificial neural network , representation (politics) , machine learning , data mining , mathematics , geometry , politics , political science , law
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.