Deep Spectral Clustering using Dual Autoencoder Network

04/30/2019
by   Xu Yang, et al.
0

The clustering methods have recently absorbed even-increasing attention in learning and vision. Deep clustering combines embedding and clustering together to obtain optimal embedding subspace for clustering, which can be more effective compared with conventional clustering methods. In this paper, we propose a joint learning framework for discriminative embedding and spectral clustering. We first devise a dual autoencoder network, which enforces the reconstruction constraint for the latent representations and their noisy versions, to embed the inputs into a latent space for clustering. As such the learned latent representations can be more robust to noise. Then the mutual information estimation is utilized to provide more discriminative information from the inputs. Furthermore, a deep spectral clustering method is applied to embed the latent representations into the eigenspace and subsequently clusters them, which can fully exploit the relationship between inputs to achieve optimal clustering results. Experimental results on benchmark datasets show that our method can significantly outperform state-of-the-art clustering approaches.

READ FULL TEXT

page 3

page 6

research
01/08/2019

Spectral Clustering via Ensemble Deep Autoencoder Learning (SC-EDAE)

Recently, a number of works have studied clustering strategies that comb...
research
12/25/2020

Learning Robust Representation for Clustering through Locality Preserving Variational Discriminative Network

Clustering is one of the fundamental problems in unsupervised learning. ...
research
09/26/2019

Adversarial Deep Embedded Clustering: on a better trade-off between Feature Randomness and Feature Drift

Clustering using deep autoencoders has been thoroughly investigated in r...
research
07/20/2020

Deep Image Clustering with Category-Style Representation

Deep clustering which adopts deep neural networks to obtain optimal repr...
research
11/27/2019

Lifelong Spectral Clustering

In the past decades, spectral clustering (SC) has become one of the most...
research
06/04/2018

Adversarial confidence and smoothness regularizations for scalable unsupervised discriminative learning

In this paper, we consider a generic probabilistic discriminative learne...
research
07/18/2017

Discriminative Transformation Learning for Fuzzy Sparse Subspace Clustering

This paper develops a novel iterative framework for subspace clustering ...

Please sign up or login with your details

Forgot password? Click here to reset