RESIDUAL ENCODER-DECODER NETWORK FOR DEEP SUBSPACE CLUSTERING

Subspace clustering aims to cluster unlabeled data that lies in a union of low-dimensional linear subspaces. Deep subspace clustering approaches based on auto-encoders have become very popular to learn the linear representation coefficients from data. However, the training of current deep methods converges slowly, which is extremely expensive. We propose a novel Residual Encoder-Decoder network for deep Subspace Clustering (RED-SC) with skip-layer connections to accelerate the convergence, using a new strategy to generate the linear coefficients by learning the linearity of data in multiple latent spaces. Experiments show the superiority of RED-SC in training efficiency and clustering accuracy.