Hybrid Tensor Networks for Fully Supervised and Semisupervised Hyperspectral Image Classification

Hyperspectral image (HSI) is rich in spectral information and spatial information to explore the physical and chemical properties of the objects, but it also brings many difficulties to the classification task. The problems of the curse of dimensionality and spectral variability in HSIs can affect the efficiency of the classifier and cause the decline of the classification accuracy. Also, the scarcity of manually labeled samples makes it difficult for the fully supervised classifiers to obtain the best results. To this end, this article proposes several novel hybrid tensor networks (HTNs) that represent multiscale spectral–spatial patterns and low-rank features for accurate classification. Moreover, the fully supervised HTN (FHTN) is embedded within a semisupervised framework with unsupervised modules providing pseudolabels, thus creating semisupervised HTN (SHTN) to exploit unlabeled data and reduce dependence on manual annotations. With proper postprocessing techniques, misclassifications are largely reduced and accuracy is further increased. The experimental results show that the proposed HTNs exhibit good generalization and robustness. FHTN and SHTN outperform classic and advanced supervised and semisupervised models in ground object classification for HSIs.