LCMatch: Layer Cross-Based Semi-Supervised Learning for Remote Sensing Scene Classification

Ruizhe Hu, Zuoyong Li, Tao Wang, Sien Li, Yuanzheng Cai, Rong Hu, George N. Papageorgiou

Abstract: We introduce LCMatch, a novel semi-supervised scene classification framework designed to enhance the performance of remote sensing image classification. Our method improves upon the existing FixMatch framework by incorporating a hierarchical structure for pseudo-label generation. The framework consists of three key modules: hierarchical cross-random combination (HCRC), adaptive weighting mechanism, and label alignment. These modules work synergistically to generate high-quality pseudo-labels, refining model predictions, and adaptively balancing the contributions of labeled and unlabeled data during training. In addition, we conduct extensive experiments on three widely used remote sensing datasets, including AID, UCMerced, and NWPU-RESISC45. Results demonstrate that LCMatch outperforms state-of-the-art semi-supervised learning (SSL) methods in terms of classification accuracy. Specifically, LCMatch exhibits robust performance even with a very limited number of labeled samples, also effectively handling class imbalance and distinguishing challenging categories.