Exploring Hard Samples in Multiview for Few-Shot Remote Sensing Scene Classification

Few-shot remote sensing scene classification (RSSC) is of high practical value in real situations where data are scarce and annotated costly. The few-shot learner needs to identify new categories with limited examples, and the core issue of this assignment is how to prompt the model to learn transferable knowledge from a large-scale base dataset. Although current approaches based on transfer learning or meta-learning have achieved significant performance on this task, there are still two problems to be addressed: 1) as an essential characteristic of remote sensing (RS) images, spatial rotation insensitivity surprisingly remains largely unexplored and 2) the high distribution uncertainty of hard samples reduces the discriminative power of the model decision boundary. Stimulated by these, we propose a corresponding end-to-end framework termed a hard sample learning and multiview integration network (HSL-MINet). First, the multiview integration (MI) module contains a pretext task introduced to guide the knowledge transfer and a multiview-attention mechanism used to extract correlational information across different rotation views of images. Second, aiming at increasing the discrimination of the model decision boundary, the hard sample learning (HSL) module is designed to evaluate and select hard samples via a classwise adaptive threshold strategy and then decrease the uncertainty of their feature distributions by a devised triplet loss. Extensive evaluations on NWPU-RESISC45, WHU-RS19, and UCM datasets show that the effectiveness of our HSL-MINet surpasses the former state-of-the-art approaches.