Crop mapping based on satellite images time-series (SITS) holds substantial economic value in agricultural production settings, in which parcel segmentation is an essential step. Existing approaches have achieved notable advancements in SITS segmentation with predetermined sequence lengths. However, we found that these approaches overlooked the generalization capability of models across scenarios with varying temporal length, leading to markedly poor segmentation results in such cases. To address this issue, we propose TEA, a TEmporal Adaptive SITS semantic segmentation method to enhance the model's resilience under varying sequence lengths. We introduce a teacher model that encapsulates the global sequence knowledge to guide a student model with adaptive temporal input lengths. Specifically, teacher shapes the student's feature space via intermediate embedding, prototypes and soft label perspectives to realize knowledge transfer, while dynamically aggregating student model to mitigate knowledge forgetting. Finally, we introduce full-sequence reconstruction as an auxiliary task to further enhance the quality of representations across inputs of varying temporal lengths. Through extensive experiments, we demonstrate that our method brings remarkable improvements across inputs of different temporal lengths on common benchmarks. Our code will be publicly available.

翻译：基于卫星图像时间序列（SITS）的作物制图在农业生产环境中具有重要的经济价值，其中地块分割是关键步骤。现有方法在预设序列长度下进行SITS分割已取得显著进展。然而，我们发现这些方法忽视了模型在不同时序长度场景下的泛化能力，导致在此类情况下分割结果显著下降。为解决这一问题，我们提出了TEA，一种时序自适应的SITS语义分割方法，以增强模型在变化序列长度下的鲁棒性。我们引入了一个封装全局序列知识的教师模型，用以指导具有自适应时序输入长度的学生模型。具体而言，教师模型通过中间嵌入、原型和软标签视角塑造学生模型的特征空间，以实现知识迁移，同时动态聚合学生模型以缓解知识遗忘。最后，我们引入全序列重构作为辅助任务，以进一步提升模型在处理不同时序长度输入时的表征质量。通过大量实验，我们证明了该方法在常见基准测试上对不同时序长度输入均带来了显著改进。我们的代码将公开提供。