While extensive research efforts have been made in semantic image segmentation, the state-of-the-art methods still suffer from blurry boundaries and mismatched objects due to the insufficient multiscale adaptability. In this paper, we propose a two-branch convolutional neural network (CNN) approach to capture the multiscale context and the boundary information with the two branches, respectively. To capture the multiscale context, we propose to embed self-attention mechanism to the atrous spatial pyramid pooling network. To capture the boundary information, we propose to fuse the low-level features in boundary feature extraction for refining the extracted boundaries via a feature fusion layer (FFL). With FFL, our method can improve the segmentation result with clearer boundaries. A new loss function is proposed which contains a segmentation loss and a boundary loss. Experiments show that our method can predict the boundaries of objects more clearly and have better performance for small-scale objects.

中文翻译：

---

深度边界感知语义图像分割

尽管在语义图像分割方面进行了广泛的研究，但由于多尺度适应性不足，最先进的方法仍然存在边界模糊和对象不匹配的问题。在本文中，我们提出了一种两分支卷积神经网络 (CNN) 方法，分别用两个分支捕获多尺度上下文和边界信息。为了捕捉多尺度上下文，我们建议将自注意力机制嵌入到多孔空间金字塔池化网络中。为了捕获边界信息，我们建议在边界特征提取中融合低级特征，以通过特征融合层（FFL）细化提取的边界。使用 FFL，我们的方法可以改善边界更清晰的分割结果。提出了一种新的损失函数，其中包含分割损失和边界损失。实验表明，我们的方法可以更清晰地预测物体的边界，对小规模物体有更好的性能。