With the increasing demand of autonomous systems, pixelwise semantic segmentation for visual scene understanding needs to be not only accurate but also efficient for potential real-time applications. In this paper, we propose Context Aggregation Network, a dual branch convolutional neural network, with significantly lower computational costs as compared to the state-of-the-art, while maintaining a competitive prediction accuracy. Building upon the existing dual branch architectures for high-speed semantic segmentation, we design a high resolution branch for effective spatial detailing and a context branch with light-weight versions of global aggregation and local distribution blocks, potent to capture both long-range and local contextual dependencies required for accurate semantic segmentation, with low computational overheads. We evaluate our method on two semantic segmentation datasets, namely Cityscapes dataset and UAVid dataset. For Cityscapes test set, our model achieves state-of-the-art results with mIOU of 75.9%, at 76 FPS on an NVIDIA RTX 2080Ti and 8 FPS on a Jetson Xavier NX. With regards to UAVid dataset, our proposed network achieves mIOU score of 63.5% with high execution speed (15 FPS).

随着对自主系统的需求不断增加，用于视觉场景理解的像素级语义分割不仅需要准确，而且对于潜在的实时应用也需要高效。在本文中，我们提出了上下文聚合网络，这是一种双分支卷积神经网络，与最先进的技术相比，其计算成本显着降低，同时保持具有竞争力的预测准确性。基于现有的用于高速语义分割的双分支架构，我们设计了一个用于有效空间细节的高分辨率分支和一个具有轻量级版本的全局聚合和局部分布块的上下文分支，可有效捕获远程和局部准确语义分割所需的上下文相关性，计算开销低。我们在两个语义分割数据集上评估我们的方法，即 Cityscapes 数据集和 UAVid 数据集。对于 Cityscapes 测试集，我们的模型在 NVIDIA RTX 2080Ti 上以 76 FPS 和 Jetson Xavier NX 上以 75.9% 的 mIOU 实现了最先进的结果。对于 UAVid 数据集，我们提出的网络以高执行速度（15 FPS）实现了 63.5% 的 mIOU 分数。