S2DMSC: A Self-Supervised Deep Multilevel Subspace Clustering Approach for Large Hyperspectral Images

Subspace clustering (SC) has achieved remarkable success in hyperspectral images (HSIs) due to the powerful representation ability of handling high-dimensional complex data. However, most of the existing SC methods focus on linear subspace representation and ignore the more effective nonlinear representation. Besides, SC suffers from the bottlenecks, such as high computation load and memory capacity, due to the spectral decomposition of adjacency matrix for large HSIs. To overcome these limitations, we propose an end-to-end learnable network framework for large HSIs, called self-supervised deep multilevel SC (S2DMSC), which incorporates the convolutional neural network (CNN) module, MSC module, and high-quality pseudo-label-based self-supervised learning module into a unified learning framework. More concretely, the deep multilevel spatial–spectral representation from hierarchical superpixels is modeled as a sparsity-constrained self-expression module for SC to construct high-quality pseudo-labels to learn the network parameters and produce better clusters for hyperspectral pixels. Experimental results on four classical HSIs demonstrate the effectiveness of S2DMSC and exhibit superior clustering performance compared with the representative clustering methods.