论文标题
语义分割的门控路径选择网络
Gated Path Selection Network for Semantic Segmentation
论文作者
论文摘要
语义细分是一项具有挑战性的任务，需要处理大规模变化，变形和不同的观点。在本文中，我们开发了一个名为门控路径选择网络（GPSNET）的新型网络，该网络旨在学习自适应接收场。在GPSNET中，我们首先设计了一个二维多尺度网络-SuperNet，该网络密集地结合了增长的接收场的功能。为了动态选择理想的语义上下文，进一步介绍了栅极预测模块。与以前专注于在常规网格上优化样本位置的作品相反，GPSNet可以自适应地捕获自由形式的密集语义上下文。派生的自适应接收场是数据依赖性的，并且可以灵活地建模不同的对象几何变换。在两个代表性的语义细分数据集（即CityScapes和ADE20K）上，我们表明所提出的方法始终优于以前的方法，并且在没有铃铛和哨声的情况下实现了竞争性能。
Semantic segmentation is a challenging task that needs to handle large scale variations, deformations and different viewpoints. In this paper, we develop a novel network named Gated Path Selection Network (GPSNet), which aims to learn adaptive receptive fields. In GPSNet, we first design a two-dimensional multi-scale network - SuperNet, which densely incorporates features from growing receptive fields. To dynamically select desirable semantic context, a gate prediction module is further introduced. In contrast to previous works that focus on optimizing sample positions on the regular grids, GPSNet can adaptively capture free form dense semantic contexts. The derived adaptive receptive fields are data-dependent, and are flexible that can model different object geometric transformations. On two representative semantic segmentation datasets, i.e., Cityscapes, and ADE20K, we show that the proposed approach consistently outperforms previous methods and achieves competitive performance without bells and whistles.
