Residual Encoder-Decoder Network for Deep Subspace Clustering
This addresses efficiency and accuracy issues in subspace clustering for unlabeled data analysis, representing an incremental improvement over existing deep learning methods.
The paper tackles the slow training convergence problem in deep subspace clustering methods by proposing a Residual Encoder-Decoder network (RED-SC) with skip-layer connections, which achieves faster training and improved clustering accuracy compared to existing approaches.
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 solve subspace clustering problems. However, the training of current deep methods converges slowly, which is much less efficient than traditional approaches. We propose a Residual Encoder-Decoder network for deep Subspace Clustering (RED-SC), which symmetrically links convolutional and deconvolutional layers with skip-layer connections, with which the training converges much faster. We use a self-expressive layer to generate more accurate linear representation coefficients through different latent representations from multiple latent spaces. Experiments show the superiority of RED-SC in training efficiency and clustering accuracy. Moreover, we are the first one to apply residual encoder-decoder on unsupervised learning tasks.