Related Experiment Video
Updated: Aug 5, 2025
03:31
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
592
Faster SCDNet: Real-Time Semantic Segmentation Network with Split Connection and Flexible Dilated Convolution
Shu Tian1, Guangyu Yao1, Songlu Chen1
1School of Computer & Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China.
Sensors (Basel, Switzerland)
|March 30, 2023
Summary
A new semantic segmentation network, SCDNet, enhances inference speed and accuracy using a dual-path structure. This approach improves frames per second (FPS) and mean intersection over union (mIoU) for better real-world applications.
Area of Science:
- Computer Vision
- Deep Learning
- Image Segmentation
Background:
- Semantic segmentation is crucial for realistic scenarios.
- Dense connections in backbone networks improve accuracy but reduce inference speed.
Purpose of the Study:
- To propose SCDNet, a backbone network balancing speed and accuracy in semantic segmentation.
- To enhance gradient propagation efficiency and network inference speed.
Main Methods:
- Introduced a streamlined, lightweight backbone with a split connection structure for increased inference speed.
- Utilized flexible dilated convolutions with varying dilation rates for richer receptive fields.
- Implemented a three-level hierarchical module for balancing multi-resolution feature maps.
- Employed a refined, flexible, and lightweight decoder.
Main Results:
- Achieved a trade-off between accuracy and speed on Cityscapes and Camvid datasets.
- Demonstrated a 36% improvement in frames per second (FPS).
- Obtained a 0.7% improvement in mean intersection over union (mIoU) on the Cityscapes test set.
Conclusions:
- SCDNet offers a viable solution for semantic segmentation tasks requiring both high accuracy and fast inference.
- The proposed architectural components effectively address the speed-accuracy limitations of existing models.
