Semi-Supervised Manifold Learning Based Multigraph Fusion for High-Resolution Remote Sensing Image Classification

For high-resolution remote sensing image classification tasks, multiple features are usually required for better performances since single visual feature is valid only in describing one pattern of images. In this letter, we propose a novel Semi-Supervised Manifold learning based Multigraph Fusion framework (SSM-MF), in which multiple features are combined to learn a low-dimensional subspace. The obtained subspace can effectively characterize the semantic information of the features and thus benefits classification. Our framework employs a semi-supervised manner by exploiting labeled and unlabeled data and therefore enjoy three advancements: 1) discriminative information and geometric information in labeled data and the structural information in unlabeled data can be jointly utilized to enhance manifold learning; 2) our framework explores the complementary of multiple features and meanwhile avoids the curse of dimensionality; and 3) our semi-supervised learning mode makes use of information in abundant unlabeled data in real-world applications. Experiments on a remote sensing image data set validate the effectiveness of our proposed method.