DSNet: An Efficient CNN for Road Scene Segmentation

TL;DR

DSNet is a lightweight, real-time CNN architecture for road scene segmentation that balances high accuracy with low computational complexity, suitable for autonomous driving applications.

Contribution

The paper introduces DSNet, a novel efficient CNN architecture based on DenseNet components, optimized for real-time road scene segmentation.

Findings

Achieves 69.1% mIoU on Cityscapes at 0.0147s per image

Maintains high accuracy comparable to larger models

Demonstrates real-time performance on GPU hardware

Abstract

Road scene understanding is a critical component in an autonomous driving system. Although the deep learning-based road scene segmentation can achieve very high accuracy, its complexity is also very high for developing real-time applications. It is challenging to design a neural net with high accuracy and low computational complexity. To address this issue, we investigate the advantages and disadvantages of several popular CNN architectures in terms of speed, storage and segmentation accuracy. We start from the Fully Convolutional Network (FCN) with VGG, and then we study ResNet and DenseNet. Through detailed experiments, we pick up the favorable components from the existing architectures and at the end, we construct a light-weight network architecture based on the DenseNet. Our proposed network, called DSNet, demonstrates a real-time testing (inferencing) ability (on the popular GPU platform) and it maintains an accuracy comparable with most previous systems. We test our system on several datasets including the challenging Cityscapes dataset (resolution of 1024x512) with an mIoU of about 69.1 % and runtime of 0.0147 second per image on a single GTX 1080Ti. We also design a more accurate model but at the price of a slower speed, which has an mIoU of about 72.6 % on the CamVid dataset.