发表机构
CNES（法国国家空间研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对地球观测数据，提出多任务部分监督学习框架，结合混合架构与重投影损失，在仅需单任务标注下同时提升超分辨率与语义分割性能，优于现有最先进方法。
AI 中文摘要
超分辨率和语义分割已知能相互促进，尤其是在地球观测的背景下。然而，在联合模型中学习这两个任务通常需要两种任务的标注，这既不切实际又代价高昂。在本文中，我们研究了针对这两个任务的多任务部分监督学习范式，其中每个样本被假定仅具有单一任务的标注。为此，我们考察了两种多任务架构变体，即顺序变体和共享变体，然后提出了一种混合变体以及一种重投影损失，以利用共享表示并在使用语义分割训练时强制保证超分辨率的图像质量。实验结果显示，与最先进的顺序变体相比，我们的方法取得了更优的结果。源代码将发布在给定的https URL上。
英文摘要
Super-resolution and semantic segmentation are known to benefit one another, especially in the Earth observation context. However, learning both tasks in a joint model often requires both task annotations, which is impractical and expensive. In this paper, we study the multi-task partially supervised learning paradigm for both tasks, where each example is assumed to have only a single-task annotation. To that end, we examine two multi-task architectural variations, the sequential and shared variants, and then propose a hybrid variant and a re-projection loss to benefit from the shared representation and enforce image quality of super-resolution when training with semantic segmentation. Experiments show favorable results compared to the SOTA sequential variant. Source code will be published at https://github.com/lhoangan/munera.
Journal ref2026 IEEE International Conference on Image Processing (ICIP), Tampere, Finland, 2026, pp. 1-6,
DOI：10.1109/ICIP61757.2026.11630424
