High-Performance Under Sparse Annotations: Cross-Prototype Bidirectional Constrained Semi-Supervised Framework for Remote Sensing Image Semantic Segmentation (opens in new tab)

Class imbalance has long posed a significant challenge to semantic segmentation in remote sensing imagery (RSI). In semi-supervised settings, existing studies attempt to alleviate this issue through data augmentation, loss function refinement, and optimized training strategies. However, these methods generally rely on an idealized assumption that labeled and unlabeled data share the same class distribution. In practice, unlabeled data typically far exceeds labeled data in scale, making this a...