Remote sensing segmentation in real deployment is inherently continual: new semantic categories emerge, and acquisition conditions shift across seasons, cities, and sensors. Despite recent progress, many incremental approaches still treat training steps as isolated updates, which leaves representation drift and forgetting insufficiently controlled. We present ProtoFlow, a time-aware prototype dynamics framework that models class prototypes as trajectories and learns their evolution with an explicit temporal vector field. By jointly enforcing low-curvature motion and inter-class separation, ProtoFlow stabilizes prototype geometry throughout incremental learning. Experiments on standard class- and domain-incremental remote sensing benchmarks show consistent gains over strong baselines, including up to 1.5-2.0 points improvement in mIoUall, together with reduced forgetting. These results suggest that explicitly modeling temporal prototype evolution is a practical and interpretable strategy for robust continual remote sensing segmentation.

翻译：实际部署中的遥感分割本质上是连续的：新语义类别不断出现，而采集条件随季节、城市和传感器而变迁。尽管近期取得了进展，许多增量方法仍将训练步骤视为孤立更新，导致表征漂移和遗忘问题未能得到充分控制。我们提出ProtoFlow——一种时间感知的原型动力学框架，将类别原型建模为轨迹，并通过显式时间向量场学习其演化过程。通过联合施加低曲率运动与类间分离约束，ProtoFlow在整个增量学习过程中稳定了原型几何结构。在标准类增量和域增量遥感基准上的实验表明，与强基线方法相比，该方法持续获得性能提升，包括平均交并比最高提升1.5-2.0个百分点，同时遗忘程度显著降低。这些结果表明，显式建模时间原型演化为鲁棒的连续遥感分割提供了一种实用且可解释的策略。