We focus on the very challenging task of semantic segmentation for autonomous driving system. It must deliver decent semantic segmentation result for traffic critical objects real-time. In this paper, we propose a very efficient yet powerful deep neural network for driving scene semantic segmentation termed as Driving Segmentation Network (DSNet). DSNet achieves state-of-the-art balance between accuracy and inference speed through efficient units and architecture design inspired by ShuffleNet V2 and ENet. More importantly, DSNet highlights classes most critical with driving decision making through our novel Driving Importance-weighted Loss. We evaluate DSNet on Cityscapes dataset, our DSNet achieves 71.8% mean Intersection-over-Union (IoU) on validation set and 69.3% on test set. Class-wise IoU scores show that Driving Importance-weighted Loss could improve most driving critical classes by a large margin. Compared with ENet, DSNet is 18.9% more accurate and 1.1+ times faster which implies great potential for autonomous driving application.

翻译：我们专注于自动驾驶系统极具挑战性的语义分解任务。 它必须实时为交通关键对象提供像样的语义分解结果。 在本文中, 我们提出一个高效而强大的深神经网络, 用于驱动场的语义分解( DSNet ) 。 DSNet 通过由 ShuffleNet V2 和 ENet 所启发的有效单位和建筑设计, 实现了准确和推导速度之间的最先进的平衡。 更重要的是, DSNet 突出一些最关键的类别, 通过我们的新颖的驾驶权重度加权损失来进行驾驶决策。 我们评估了城市景数据集的 DSNet, 我们的DSNet 实现了71.8% 的平均跨区间断层分解( IoU), 测试集达到69. 3% 。 lex- IoU 分数显示, 驾驶权重度损失可以大大改善最关键的类别。 与 ENet 相比, DSNet 更准确 18.9 和 1. 1 + 倍, 意味着自主驱动应用的巨大潜力 。