In this paper, we focus on designing effective method for fast and accurate scene parsing. A
common practice to improve the performance is to attain high resolution feature maps with
strong semantic representation. Two strategies are widely used—atrous convolutions and
feature pyramid fusion, are either computation intensive or ineffective. Inspired by the Optical
Flow for motion alignment between adjacent video frames, we propose a Flow Alignment
Module (FAM) to learn Semantic Flow between feature maps of adjacent levels, and …

Detailed improvement on baseline models: Table 1 compares the detailed results of each
category on the validation set, where ResNet-101 is used as backbone, and FPN decoder
with PPM head serves as the baseline. Our method improves almost all categories,
especially for'truck'with more than 19% mIoU improvement. More structured feature
visualization on FAM: We give more structured feature visualization in Figure 1. We visualize
more FAM outputs with two different location: last stages (below the blue line) and next to the …