Deep spectral clustering using dual autoencoder network

Yang, Xu1; Deng, Cheng1; Zheng, Feng2; Yan, Junchi3; Liu, Wei4

10.1109/CVPR.2019.00419

2019

1063-6919

978-1-7281-3294-5

32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019

2019-June

4061-4070

15-20 June 2019

Long Beach, CA, United states

10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA

IEEE Computer Society

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.
© 2019 IEEE.

Representation Learning Statistical Learning

其他

英语

EI ; CPCI-S

[2017YFE0104100] ; [2018ZDXM-GY-176] ; National Natural Science Foundation of China[61602176]

Computer Science

Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods

WOS:000529484004025

20200508114705

Deep learning ; Clustering algorithms ; Embeddings ; Computer vision

Ergonomics and Human Factors Engineering:461.4 ; Computer Software, Data Handling and Applications:723 ; Artificial Intelligence:723.4 ; Computer Applications:723.5 ; Vision:741.2 ; Information Sources and Analysis:903.1

EV Compendex

1.School of Electronic Engineering, Xidian University, Xian; 710071, China
2.Department of Computer Science and Engineering, Southern University of Science and Technology, China
3.Department of CSE, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, China
4.Tencent AI Lab, Shenzhen, China

Yang, Xu,Deng, Cheng,Zheng, Feng,et al. Deep spectral clustering using dual autoencoder network[C]. 10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA:IEEE Computer Society,2019:4061-4070.