This paper introduces an extremely efficient CNN architecture named DFANet for semantic segmentation under resource constraints. Our proposed network starts from a single lightweight backbone and aggregates discriminative features through sub-network and sub-stage cascade respectively. Based on the multi-scale feature propagation, DFANet substantially reduces the number of parameters, but still obtains sufficient receptive field and enhances the model learning ability, which strikes a balance between the speed and segmentation performance. Experiments on Cityscapes and CamVid datasets demonstrate the superior performance of DFANet with 8$\times$ less FLOPs and 2$\times$ faster than the existing state-of-the-art real-time semantic segmentation methods while providing comparable accuracy. Specifically, it achieves 70.3\% Mean IOU on the Cityscapes test dataset with only 1.7 GFLOPs and a speed of 160 FPS on one NVIDIA Titan X card, and 71.3\% Mean IOU with 3.4 GFLOPs while inferring on a higher resolution image.

本文提出了一种名为DFANet的极其高效的卷积神经网络架构，用于在资源有限的情况下进行语义分割。通过子网络和子阶段级联聚合区分特征，通过多尺度特征传播，DFANet大大减少了参数数量，并提高了模型学习能力，在速度和分割性能之间取得平衡。在Cityscapes和CamVid数据集上的实验证明了DFANet具有比现有最先进的实时语义分割方法快2倍，FLOPs少8倍的卓越性能，同时提供可比较的准确性。具体而言，它在Cityscapes测试数据集上实现了70.3％的IOU平均值，仅使用1.7 GFLOPs，并在一张NVIDIA Titan X卡上以160 FPS的速度进行推断，在更高分辨率图像上推断时，实现了71.3％的IOU平均值和3.4 GFLOPs。

DFANet: 深度特征聚合实时语义分割