超调(微波通信)
计算机科学
背景(考古学)
推论
分割
PID控制器
人工智能
解析
控制器(灌溉)
边界(拓扑)
控制理论(社会学)
算法
计算机视觉
模式识别(心理学)
数学
控制工程
控制(管理)
工程类
数学分析
古生物学
生物
电信
温度控制
农学
作者
Jiacong Xu,Zixiang Xiong,Shankar Prasad Bhattacharyya
出处
期刊:Proceedings
[Institute of Electrical and Electronics Engineers]
日期:2023-06-01
卷期号:: 19529-19539
被引量:1091
标识
DOI:10.1109/cvpr52729.2023.01871
摘要
Two-branch network architecture has shown its efficiency and effectiveness in real-time semantic segmentation tasks. However, direct fusion of high-resolution details and low-frequency context has the drawback of detailed features being easily overwhelmed by surrounding contextual information. This overshoot phenomenon limits the improvement of the segmentation accuracy of existing two-branch models. In this paper, we make a connection between Convolutional Neural Networks (CNN) and Proportional-Integral-Derivative (PID) controllers and reveal that a two-branch network is equivalent to a Proportional-Integral (PI) controller, which inherently suffers from similar overshoot issues. To alleviate this problem, we propose a novel three-branch network architecture: PIDNet, which contains three branches to parse detailed, context and boundary information, respectively, and employs boundary attention to guide the fusion of detailed and context branches. Our family of PIDNets achieve the best trade-off between inference speed and accuracy and their accuracy surpasses all the existing models with similar inference speed on the Cityscapes and CamVid datasets. Specifically, PIDNet-S achieves 78.6% mIOU with inference speed of 93.2 FPS on Cityscapes and 80.1% mIOU with speed of 153.7 FPS on CamVid.
科研通智能强力驱动
Strongly Powered by AbleSci AI