Real-Time Semantic Segmentation via Multiply Spatial Fusion Network

TL;DR

This paper introduces MSFNet, an efficient CNN for real-time semantic segmentation that balances speed and accuracy, suitable for industry applications like autonomous driving.

Contribution

The paper proposes MSFNet with a Multi-features Fusion Module and Class Boundary Supervision to enhance spatial information and boundary accuracy in real-time segmentation.

Findings

Achieves 77.1% Mean IOU at 41 FPS on Cityscapes.

Achieves 75.4% Mean IOU at 91 FPS on Camvid.

Outperforms existing approaches in speed and accuracy.

Abstract

Real-time semantic segmentation plays a significant role in industry applications, such as autonomous driving, robotics and so on. It is a challenging task as both efficiency and performance need to be considered simultaneously. To address such a complex task, this paper proposes an efficient CNN called Multiply Spatial Fusion Network (MSFNet) to achieve fast and accurate perception. The proposed MSFNet uses Class Boundary Supervision to process the relevant boundary information based on our proposed Multi-features Fusion Module which can obtain spatial information and enlarge receptive field. Therefore, the final upsampling of the feature maps of 1/8 original image size can achieve impressive results while maintaining a high speed. Experiments on Cityscapes and Camvid datasets show an obvious advantage of the proposed approach compared with the existing approaches. Specifically, it achieves 77.1% Mean IOU on the Cityscapes test dataset with the speed of 41 FPS for a 1024*2048 input, and 75.4% Mean IOU with the speed of 91 FPS on the Camvid test dataset.