RSProtoSeg: High Spatial Resolution Remote Sensing Images Segmentation Based on Non-Learnable Prototypes
Wenjie Sun, Jie Zhang, Yujie Lei, Danfeng Hong
Abstract
Semantic segmentation of high spatial resolution remote sensing images presents unique challenges due to the imbalanced foreground-background distribution and large intra-class variance. This study proposes a novel semantic segmentation algorithm based on non-learnable prototypes, named RSProtoSeg. This approach optimizes the spatial relationship between foreground-background prototypes and intra-class prototypes. Specifically, we propose a foreground-background distance optimization loss function to enhance sparsity between these phototypes, effectively mitigating foreground-background distribution imbalances. Moreover, we introduce an online discrete clustering module that represents each class with a set of prototypes and adds an adaptive regular term penalty to promote sparse structure and reduce the variance issue. Evaluation on three remote sensing datasets (iSAID, ISPRS Potsdam, and Vaihingen) demonstrates significant accuracy improvements, aligning our approach with state-of-the-art methods. Our non-learnable prototype-based approach offers a promising solution for semantic segmentation in high spatial resolution remote sensing images.