DSL-BC: Deep Subspace Learning With Boundary Consistency for Hyperspectral Image Classification

Deep subspace learning (DSL) plays an essential role in hyperspectral image (HSI) classification, providing an effective solution tool to reduce the redundant information of HSI pixels. Semisupervised convolutional neural network (SSCNN)-based DSL methods can extract a more representative representation of latent subspace with the help of the labeled and unlabeled data. However, CNN-based DSL methods may lose the information on the class boundaries leading to misclassifications within regular input. We develop the DSL method with boundary consistency (DSL-BC) for the HSI classification to address this problem. In DSL-BC, the convolutional autoencoder (CAE) is first applied to extract the deep subspace representation (DSR). The DSR is used to model the boundary consistency. The graph convolutional network (GCN) is further adapted to enforce the boundary consistency by conducting the graph convolution on arbitrarily structured non-Euclidean data and irregular image regions. In addition, the adaptive entropy rate (ER) superpixel segmentation algorithm is applied to generate superpixels, and superpixel constraint is employed to improve the ability of DSL and GCN construction. DSL-BC integrates the DSL, the GCN, and the superpixel constraint into a unified objective function. A customized iterative algorithm is used to solve the objective function of the DSL-BC. The experimental results on three challenging public HSI datasets demonstrate that the DSL-BC can outperform the related state-of-the-art HSI classification methods.