利用低层表示实现超快速道路分割
Exploiting Low-level Representations for Ultra-Fast Road Segmentation
AI总结：
提出LFD-RoadSeg，利用低层特征主导的双边网络实现超快速道路分割，在KITTI-Road上达到95.21% MaxF和238 FPS，模型仅936k参数。
摘要：
在嵌入式平台上实现实时性和准确性一直是道路分割方法追求的目标。为此，研究者们提出了许多轻量级网络。然而，这些方法忽略了道路是“stuff”（背景或环境元素）而非“things”（特定的可识别对象）这一事实，这启发我们探索使用低层特征而非高层特征来表示道路的可行性。令人惊讶的是，我们发现主流网络模型的第一阶段就足以表示道路的大部分像素以进行分割。受此启发，我们提出了低层特征主导的道路分割网络（LFD-RoadSeg）。具体来说，LFD-RoadSeg采用双边结构。首先设计空间细节分支，通过ResNet-18的第一阶段提取道路的低层特征表示。为了抑制低层特征中纹理缺失区域被误认为道路的情况，随后设计上下文语义分支以快速方式提取上下文特征。为此，在第二个分支中，我们对输入图像进行非对称下采样，并设计了一个聚合模块，以实现与ResNet-18第三阶段相当的感受野，但耗时更少。最后，为了从低层特征中分割出道路，我们提出了一个选择性融合模块，用于计算低层表示与上下文特征之间的逐像素注意力，并通过该注意力抑制非道路的低层响应。在KITTI-Road上，LFD-RoadSeg实现了95.21%的最大F1值（MaxF）和93.71%的平均精度，同时在单个TITAN Xp上达到238 FPS，在Jetson TX2上达到54 FPS，模型大小仅为936k参数。源代码可在https://github.com/zhouhuan-hust/LFD-RoadSeg获取。
英文摘要：
Achieving real-time and accuracy on embedded platforms has always been the pursuit of road segmentation methods. To this end, they have proposed many lightweight networks. However, they ignore the fact that roads are "stuff" (background or environmental elements) rather than "things" (specific identifiable objects), which inspires us to explore the feasibility of representing roads with low-level instead of high-level features. Surprisingly, we find that the primary stage of mainstream network models is sufficient to represent most pixels of the road for segmentation. Motivated by this, we propose a Low-level Feature Dominated Road Segmentation network (LFD-RoadSeg). Specifically, LFD-RoadSeg employs a bilateral structure. The spatial detail branch is firstly designed to extract low-level feature representation for the road by the first stage of ResNet-18. To suppress texture-less regions mistaken as the road in the low-level feature, the context semantic branch is then designed to extract the context feature in a fast manner. To this end, in the second branch, we asymmetrically downsample the input image and design an aggregation module to achieve comparable receptive fields to the third stage of ResNet-18 but with less time consumption. Finally, to segment the road from the low-level feature, a selective fusion module is proposed to calculate pixel-wise attention between the low-level representation and context feature, and suppress the non-road low-level response by this attention. On KITTI-Road, LFD-RoadSeg achieves a maximum F1-measure (MaxF) of 95.21% and an average precision of 93.71%, while reaching 238 FPS on a single TITAN Xp and 54 FPS on a Jetson TX2, all with a compact model size of just 936k parameters. The source code is available at https://github.com/zhouhuan-hust/LFD-RoadSeg.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
