CLPM: A Hybrid Network With Cross-Space Learning and Perception-Driven Mechanism for Long-Tailed Remote Sensing Image Classification

Long-tailed distribution is a common issue in remote sensing image classification (RSIC), and many datasets suffer from severe class imbalance. This imbalance often causes the classifier to focus on the head classes with more samples, neglecting the tail classes. As a result, the precision of the tail classes is reduced, which in turn affects the generalization ability of the classifier. To address this problem, a hybrid network based on cross-space learning and perception-driven mechanism (CLPM) is proposed to improve the classification accuracy of samples from the tail classes. The CLPM network consists of three components. The cross-space representation learning branch is designed to enhance the representation capability of tail-class samples by integrating multiscale and multiregion spatial features. In parallel, the adaptive perception classification branch dynamically adjusts the receptive fields to improve generalization across different resolutions and challenging scenarios. In addition, the CLPM innovatively applies the von Mises-Fisher (vMF) distribution to remote sensing images for high-dimensional interclass feature modeling. Building on this, a vMF-based contrastive loss function is proposed. This approach effectively coordinates the learning processes of head and tail classes while enhancing the precision of feature representation. The effectiveness of CLPM is validated on datasets with varying balance ratios, including SIRI-WHU, CLRS, and NWPU-RESISC45. Results show that CLPM significantly improves tail classes accuracy while maintaining high recognition rates for head and middle classes. Compared with the existing methods, CLPM has significant advantages in the overall recognition accuracy, the long-tailed problem, and diversity adaptation.