Deep subspace clustering networks

Date

2017

Authors

Ji, Pan
Zhang, Tong
Li, Hongdong
Salzmann, Mathieu
Reid, Ian

Journal Title

Journal ISSN

Volume Title

Publisher

Neural Information Processing Systems Foundation

Abstract

We present a novel deep neural network architecture for unsupervised subspace clustering. This architecture is built upon deep auto-encoders, which non-linearly map the input data into a latent space. Our key idea is to introduce a novel self-expressive layer between the encoder and the decoder to mimic the "self-expressiveness" property that has proven effective in traditional subspace clustering. Being differentiable, our new self-expressive layer provides a simple but effective way to learn pairwise affinities between all data points through a standard back-propagation procedure. Being nonlinear, our neural-network based method is able to cluster data points having complex (often nonlinear) structures. We further propose pre-training and fine-tuning strategies that let us effectively learn the parameters of our subspace clustering networks. Our experiments show that our method significantly outperforms the state-of-the-art unsupervised subspace clustering techniques.

Description

Keywords

Citation

Source

Proceedings of the 31st Annual Conference on Neural Information Processing Systems, NIPS 2017

Type

Conference paper

Book Title

Entity type

Access Statement

Open Access

License Rights

Restricted until