Semantic segmentation is an important yet unsolved problem in aerial scenes understanding. One of the major challenges is the intense variations of scenes and object scales. In this article, we propose a novel multi-scale aware-relation network (MANet) to tackle this problem in remote sensing. Inspired by the process of human perception of multi-scale (MS) information, we explore discriminative and diverse MS representations. For discriminative MS representations, we propose an inter-class and intra-class region refinement (IIRR) method to reduce feature redundancy caused by fusion. IIRR utilizes the refinement maps with intra-class and inter-class scale variation to guide MS fine-grained features. Then, we propose multi-scale collaborative learning (MCL) to enhance the diversity of MS feature representations. The MCL constrains the diversity of MS feature network parameters to obtain diverse information. Also, the segmentation results are rectified according to the dispersion of the multilevel network predictions. In this way, MANet can learn MS features by collaboratively exploiting the correlation among different scales. Extensive experiments on image and video datasets, which have large-scale variations, have demonstrated the effectiveness of our proposed MANet.

中文翻译：

---

MANet：用于航空场景语义分割的多尺度感知关系网络


语义分割是航空场景理解中一个重要但尚未解决的问题。主要挑战之一是场景和物体尺度的剧烈变化。在本文中，我们提出了一种新颖的多尺度感知关系网络（MANet）来解决遥感中的这一问题。受人类感知多尺度（MS）信息过程的启发，我们探索有区别的和多样化的 MS 表示。对于判别性 MS 表示，我们提出了一种类间和类内区域细化（IIRR）方法来减少融合引起的特征冗余。 IIRR 利用具有类内和类间尺度变化的细化图来指导 MS 细粒度特征。然后，我们提出多尺度协作学习（MCL）来增强 MS 特征表示的多样性。 MCL约束MS特征网络参数的多样性以获得多样化的信息。此外，根据多级网络预测的分散性对分割结果进行修正。通过这种方式，MANet 可以通过协作利用不同尺度之间的相关性来学习 MS 特征。对具有大规模变化的图像和视频数据集的大量实验证明了我们提出的 MANet 的有效性。