LAUSR

Labeling hyperspectral images (HSIs) is time-consuming and labor-intensive for researchers, so the deficiency of adequate labeling samples is a giant obstacle to conducting HSI classification. Especially, such an issue is exacerbated when there are no available labeled samples in the target scene. For the sake of resolving the aforesaid issue, we put forward a novel cross-scene HSI classification method namely a bi-classifier adversarial network (BCAN) to transfer knowledge from a similar but different source domain to an unlabeled target domain. First, the source and target domain distributions are aligned by maximizing and minimizing the decision discrepancy between the two classifiers, respectively. Then, more accurate samples corresponding to pseudo-labels are selected as reliable samples and added to the training set. Finally, the spectral band random zeroing (SBRZ) method is proposed to expand the training samples for reliable samples, which handles the problem of insufficient network training resulting from insufficient samples in the source domain. By using multiclassifiers for domain adaptation and data augmentation, the accuracy of the network for cross-scene HSI classification tasks is improved. BCAN can extract the source domain’s helpful information to complete the target domain classification task. Experiments conducted on ten HSI data pairs show that BCAN outperforms many state-of-the-art baselines.