通过轨迹建模原型演变，减少遥感分割中的遗忘问题。
ProtoFlow: Mitigating Forgetting in Class-Incremental Remote Sensing Segmentation via Low-Curvature Prototype Flow
- 将类别原型视为时间轨迹，用低曲率向量场建模其动态演化
- 在标准增量学习基准上提升mIoUall达1.5-2.0点，遗忘显著减少
- 适合需要长期稳定部署的遥感图像分割场景
真实场景中的遥感图像分割具有持续性特征：新语义类别不断出现，且受季节、城市与传感器差异影响。尽管近期进展显著，多数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控制不足。本文提出ProtoFlow，一种时序感知的原型动态框架，将类别原型建模为轨迹，并通过显式的时间向量场学习其演化过程。通过联合约束低曲率运动与类间分离，有效稳定了增量学习过程中原型几何结构。在标准的类别与领域增量遥感分割基准上，实验表明该方法持续优于强基线模型，mIoUall提升达1.5-2.0点，同时显著降低遗忘率。结果表明，显式建模原型随时间演化是一种可行且可解释的鲁棒持续遥感分割策略。开源代码：https://github.com/dudududke/protoflow。
原文摘要 · Abstract (English)
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. Open-source code:https://github.com/dudududke/protoflow.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。