Cross-Domain Distribution Calibration of Hyperspectral Image Classification

Due to the huge number of trainable parameters, deep learning-based hyperspectral image (HSI) classification method frequently struggle to achieve satisfactory accuracy when providing small amount of labeled training samples. This study proposes a novel few-shot transfer learning-based HSI classification method, which can exploit samples from multiple other HSI datasets (termed as multisource domain) to address the issues of limited labeled samples in target domain. For this purpose, we first construct a feature extractor utilizing both convolution neural network (CNN) and transformer. Specifically, CNN extracts features of HSI in spatial domain, while transformer is used to capture both global and local features within spectral domain. Since the constructed feature extractor is trained on multiple HSIs from source domain, it has a good generalization ability. Then, we propose to utilize the distribution calibration to decrease the difference between the features of the source domain and the target domain. By selecting samples with similar distribution with the target domain from the multisource domain for distribution calibration, the generalization ability of the proposed method for the target domain classification HSI is further enhanced. Experimental results demonstrate the proposed method has better HSI classification results compared with other competing methods.