MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation
This addresses the need for efficient segmentation in applications like autonomous driving, though it appears incremental as it builds on existing lightweight architectures.
The paper tackles the trade-off between accuracy and speed in real-time semantic segmentation by proposing MSCFNet, a lightweight network with multi-scale context fusion that achieves 71.9% Mean IoU on Cityscapes with only 1.15M parameters and runs at over 50 FPS.
In recent years, how to strike a good trade-off between accuracy and inference speed has become the core issue for real-time semantic segmentation applications, which plays a vital role in real-world scenarios such as autonomous driving systems and drones. In this study, we devise a novel lightweight network using a multi-scale context fusion (MSCFNet) scheme, which explores an asymmetric encoder-decoder architecture to dispose this problem. More specifically, the encoder adopts some developed efficient asymmetric residual (EAR) modules, which are composed of factorization depth-wise convolution and dilation convolution. Meanwhile, instead of complicated computation, simple deconvolution is applied in the decoder to further reduce the amount of parameters while still maintaining high segmentation accuracy. Also, MSCFNet has branches with efficient attention modules from different stages of the network to well capture multi-scale contextual information. Then we combine them before the final classification to enhance the expression of the features and improve the segmentation efficiency. Comprehensive experiments on challenging datasets have demonstrated that the proposed MSCFNet, which contains only 1.15M parameters, achieves 71.9\% Mean IoU on the Cityscapes testing dataset and can run at over 50 FPS on a single Titan XP GPU configuration.