PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers

🤖 Plain-English Summary

Two-branch network architecture has shown its efficiency and effectiveness in real-time semantic segmentation tasks. 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.

🔑 Key Findings

• 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.

🔗 Related Resources