论文标题
PIDNET：由PID控制器启发的实时语义分割网络
PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers
论文作者
论文摘要
两个分支网络体系结构显示了其在实时语义细分任务中的效率和有效性。但是，高分辨率细节和低频上下文的直接融合使详细特征的缺点很容易被周围的上下文信息淹没。这种过冲现象限制了现有两部分模型的分割精度的提高。在本文中，我们在卷积神经网络（CNN）和比例综合衍生物（PID）控制器之间建立了联系，并揭示了两个分支网络等同于比例综合（PI）控制器，这些控制器固有地遭受了类似的过冲问题。为了减轻这个问题，我们提出了一个新颖的三个分支网络架构：PIDNET，其中包含三个分支以详细说明，上下文和边界信息，并采用边界关注来指导详细和上下文分支的融合。我们的Pidnet家族在推理速度和准确性之间实现了最佳的权衡，其准确性超过了所有现有模型，其推理速度在CityScapes和Camvid数据集上具有相似的推理速度。具体而言，Pidnet-S在CityScapes上的推理速度为93.2 fps，在Camvid上的推理速度为93.2 fps，速度为93.2 fps，速度为80.1％，Camvid上的推理速度为93.2 fps，在CAMVID上的推理速度为93.2 fps。
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.
