The encoder-decoder framework is state-of-the-art for offline semantic image segmentation. Since the rise in autonomous systems, real-time computation is increasingly desirable. In this paper, we introduce fast segmentation convolutional neural network (Fast-SCNN), an above real-time semantic segmentation model on high resolution image data (1024x2048px) suited to efficient computation on embedded devices with low memory. Building on existing two-branch methods for fast segmentation, we introduce our `learning to downsample' module which computes low-level features for multiple resolution branches simultaneously. Our network combines spatial detail at high resolution with deep features extracted at lower resolution, yielding an accuracy of 68.0% mean intersection over union at 123.5 frames per second on Cityscapes. We also show that large scale pre-training is unnecessary. We thoroughly validate our metric in experiments with ImageNet pre-training and the coarse labeled data of Cityscapes. Finally, we show even faster computation with competitive results on subsampled inputs, without any network modifications.

本文介绍了一种快速分割卷积神经网络（Fast-SCNN），它是一种高分辨率图像数据（1024x2048px）的半实时语义分割模型，适用于在低内存嵌入式设备上进行高效计算。该网络通过在多个分辨率分支上同时计算低级特征和高级特征，实现了高分辨率的空间细节与更低分辨率下提取的深度特征的结合，并在Cityscapes数据集上以每秒123.5帧的速度获得了68.0％的平均交并比准确率。实验证明，预先培训规模的大规模预处理是不必要的。

Fast-SCNN: 快速语义分割网络