School of Computer & Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China.
Sensors (Basel). 2023 Mar 14;23(6):3112. doi: 10.3390/s23063112.
Recently, semantic segmentation has been widely applied in various realistic scenarios. Many semantic segmentation backbone networks use various forms of dense connection to improve the efficiency of gradient propagation in the network. They achieve excellent segmentation accuracy but lack inference speed. Therefore, we propose a backbone network SCDNet with a dual path structure and higher speed and accuracy. Firstly, we propose a split connection structure, which is a streamlined lightweight backbone with a parallel structure to increase inference speed. Secondly, we introduce a flexible dilated convolution using different dilation rates so that the network can have richer receptive fields to perceive objects. Then, we propose a three-level hierarchical module to effectively balance the feature maps with multiple resolutions. Finally, a refined flexible and lightweight decoder is utilized. Our work achieves a trade-off of accuracy and speed on the Cityscapes and Camvid datasets. Specifically, we obtain a 36% improvement in FPS and a 0.7% improvement in mIoU on the Cityscapes test set.
最近，语义分割在各种现实场景中得到了广泛应用。许多语义分割骨干网络使用各种形式的密集连接来提高网络中梯度传播的效率。它们实现了优异的分割精度，但缺乏推理速度。因此，我们提出了一种具有双路径结构的骨干网络 SCDNet，以实现更高的速度和精度。首先，我们提出了一种分割连接结构，这是一种流线型的轻量级骨干网络，具有并行结构，可提高推理速度。其次，我们引入了一种灵活的扩张卷积，使用不同的扩张率，使网络能够具有更丰富的感受野来感知物体。然后，我们提出了一个三级分层模块，以有效地平衡具有多个分辨率的特征图。最后，使用了一个精细化的灵活轻量级解码器。我们的工作在 Cityscapes 和 Camvid 数据集上实现了准确性和速度之间的权衡。具体来说，我们在 Cityscapes 测试集上获得了 36%的帧率提高和 0.7%的 mIoU 提高。
Zotero 插件
