论文标题
关于语义细分的子空间金字塔融合网络的技术报告
Technical Report on Subspace Pyramid Fusion Network for Semantic Segmentation
论文作者
论文摘要
以下是一份技术报告，用于测试所提出的子空间金字塔融合模块（SPFM）捕获多尺度特征表示的有效性，这对于语义分割更有用。在这项调查中，我们提出了有效的洗牌注意模块（ESAM），以通过融合多级全局上下文特征来重建跳过连接路径。在包括Camvid和CityScapes在内的两个知名语义分割数据集的实验结果显示了我们提出的方法的有效性。
The following is a technical report to test the validity of the proposed Subspace Pyramid Fusion Module (SPFM) to capture multi-scale feature representations, which is more useful for semantic segmentation. In this investigation, we have proposed the Efficient Shuffle Attention Module(ESAM) to reconstruct the skip-connections paths by fusing multi-level global context features. Experimental results on two well-known semantic segmentation datasets, including Camvid and Cityscapes, show the effectiveness of our proposed method.
