Semantic segmentation plays a vital role in image understanding. Recent studies have attempted to achieve precise pixel-level classification by using deep networks that provide hierarchical features. These methods are trying to effectively utilise multi-level features that are extracted from the data and precisely reconstruct some characteristics of objects that are lost in producing high-level features. In this paper, we propose a multi-scale context U-net (MSCU-net) for semantic image segmentation. This network uses a multi-scale context block (MSCB) to aggregate multi-level features and employs the CRF layer to explicitly model the dependencies among pixels. This network significantly outperforms other state-of-the-art methods on both the PASCAL VOC 2012 and Cityscapes datasets.

语义分割在图像理解中起着至关重要的作用。最近的研究试图通过使用提供分层特征的深度网络来实现精确的像素级分类。这些方法试图有效地利用从数据中提取的多级特征，并精确重建在生成高级特征时丢失的对象的某些特征。在本文中，我们提出了一种用于语义图像分割的多尺度上下文 U-net（MSCU-net）。该网络使用多尺度上下文块 (MSCB) 来聚合多级特征，并使用 CRF 层对像素之间的依赖关系进行显式建模。该网络在 PASCAL VOC 2012 和 Cityscapes 数据集上的性能明显优于其他最先进的方法。