Semantic Flow for Fast and Accurate Scene Parsing
This addresses the need for real-time scene parsing in applications like autonomous driving, with incremental improvements in speed and accuracy over existing methods.
The paper tackles the problem of achieving fast and accurate scene parsing by proposing a Flow Alignment Module (FAM) that learns Semantic Flow to efficiently broadcast high-level features to high-resolution ones, resulting in a method that achieves 80.4% mIoU on Cityscapes at 26 FPS.
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 broadcast high-level features to high resolution features effectively and efficiently. Furthermore, integrating our module to a common feature pyramid structure exhibits superior performance over other real-time methods even on light-weight backbone networks, such as ResNet-18. Extensive experiments are conducted on several challenging datasets, including Cityscapes, PASCAL Context, ADE20K and CamVid. Especially, our network is the first to achieve 80.4\% mIoU on Cityscapes with a frame rate of 26 FPS. The code is available at \url{https://github.com/lxtGH/SFSegNets}.