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.

中文翻译：

---

用于语义分割的门控路径选择网络

语义分割是一项具有挑战性的任务，需要处理大规模的变化、变形和不同的观点。在本文中，我们开发了一种名为门控路径选择网络 (GPSNet) 的新型网络，旨在学习自适应感受野。在 GPSNet 中，我们首先设计了一个二维多尺度网络 - SuperNet，它密集地结合了不断增长的感受野的特征。为了动态选择所需的语义上下文，进一步引入了门预测模块。与之前专注于优化规则网格上的样本位置的工作相比，GPSNet 可以自适应地捕获自由形式的密集语义上下文。派生的自适应感受野依赖于数据，并且可以灵活地模拟不同对象的几何变换。在两个有代表性的语义分割数据集上，即