Masked Superpixel Contrastive Subspace Clustering Network for Unsupervised Large-Scale Hyperspectral Image Classification

Subspace clustering (SSC) contributes a lot to the development of unsupervised hyperspectral image (HSI) classification task due to its ability of processing high-dimensional data. In general, SSC suffers from the bottlenecks of high computational cost when dealing with large-scale HSI. Some studies address this problem by using superpixel segmentation. However, the introduction of superpixel segmentation may cause some adverse effects, including interference from nontarget region samples and the oversmoothing of superpixel-level samples. To overcome these issues, we propose a masked superpixel contrastive subspace clustering (MSCSC) for large-scale HSI classification. Specifically, we leverage hyperspectral masked autoencoder (HMAE) rather than conventional autoencoder (CAE) as the backbone to mitigate the interference of nontarget region samples during feature extraction. Then, based on this backbone, we integrate contrastive learning (CL) with self-expressiveness-based SSC to form the superpixel-level contrastive SSC network, which aims to learn the discriminative superpixel-level self-representation. Moreover, we design a novel data augmentation strategy to ensure learn global and local information, improving the distinguishability of superpixel-level features. Experiments on four popular HSI datasets validate the superiority of our proposed method, with a large accuracy improvement compared with state-of-the-art methods.