Multi-scale object recognition and accurate object localization are two major problems for semantic segmentation in high resolution aerial images. To handle these problems, we design a Context Fuse Module to aggregate multi-scale features and propose an Attention Mix Module to combine different level features for higher localization accuracy. We further employ a Residual Convolutional Module to refine features in all levels. Based on these modules, we construct a new end-to-end network for semantic labeling in aerial images.
Experiments demonstrate that our network outperforms other state-of-the-art models on the large-scale ISPRS Vaihingen 2D Semantic Labeling Challenge dataset. The model implementation code is made publicly available.