BriefGPT.xyz
Dec, 2016
金字塔场景解析网络
Pyramid Scene Parsing Network
HTML
PDF
Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, Jiaya Jia
TL;DR
本文介绍了一种利用基于不同区域的上下文聚合和金字塔场景分割网络的全局上下文信息的方法，以进行场景分割任务，并在各种数据集上取得了最先进的性能表现。该方法在PASCAL VOC 2012基准和Cityscapes基准数据集上创造了新的记录。
Abstract
scene parsing
is challenging for unrestricted open vocabulary and diverse scenes. In this paper, we exploit the capability of
global context information
by different-region-based context aggregation through our p
→