Domain-Adaptive Few-Shot Learning for Hyperspectral Image Classification

Recently, hyperspectral image (HSI) classification by deep learning is flourishing. However, only a few labeled samples are available in practice since it is time-and-labor-consuming to label pixels in HSI (called target domain). This letter proposes a domain-adaptive few-shot learning (DAFSL) method to tackle this problem. Specifically, some other HSIs (called source domain) with large labeled samples are fully used as complementary information and a generative architecture is employed to adapt embedded features in the source domain to that of the target domain. We first perform domain adaptation with unsupervised learning. In detail, the embedded features are generated by the encoder of an autoencoder, where both source and target samples could be well recovered and the reconstruction loss is used to measure the gap between the source domain and the target domain. At the same time, the embedded features are put into a metric space for classification in the source domain and the encoder parameter is fine-tuned together with the classifier in the target domain with few labels so that both general and discriminative features are well captured. The experiment results show that DAFSL outperforms the other mainstream methods with limited labeled samples.