Semantic Segmentation Network for Classification of Hyperspectral Images With Small Size Samples.

A sparse label-oriented semantic segmentation network (SL-SSNet) is proposed for the classification of hyperspectral images (HSIs) in this letter. Since semantic segmentation network performs pixel-level classification and can extract long-range contextual information, we apply it to the task of HSI classification. To mitigate the small size sample problem, we not only design a lightweight fully convolutional network, but also explore the usefulness of unlabeled data by introducing two constraints. First, an adversarial learning-based multiclassifier consistency strategy is employed to improve the classification of unlabeled data. It constrains two different classifiers to have consistent prediction results on unlabeled data. As a result, the extracted features of unlabeled data can be more discriminative and the predictions are more reliable. Second, a manifold regularizer is applied to constrain the classification results of unlabeled data to be smooth with respect to the data manifold, which can further exploit the unlabeled data and alleviate the small size sample problem. The experimental results using multiple hyperspectral data demonstrate the efficiency of the proposed method. [ABSTRACT FROM AUTHOR]