Skip to yearly menu bar Skip to main content


Poster

Deep Subspace Clustering Networks

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

Pacific Ballroom #17

Keywords: [ Unsupervised Learning ] [ Nonlinear Dimensionality Reduction and Manifold Learning ] [ Deep Autoencoders ]


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 the proposed method significantly outperforms the state-of-the-art unsupervised subspace clustering methods.

Live content is unavailable. Log in and register to view live content