Feature extraction and enhancement for real-time semantic segmentation

Most of the semantic segmentation real-time networks improve the segmentation speed by reducing the spatial resolution, leading to the accuracy being significantly reduced as a result. To solve this problem, we propose feature enhancement module (FEM), feature extraction and fusion module (FEFM). By extracting and enhancing the future map before the image down-sample on the backbone and fusing the low-level features with rich details and the high-level features with more semantic information. Based on the FEM and FEFM, we introduce a real-time semantic segmentation network feature extraction and enhancement network. In the experiment, using Cityscapes and CamVid datasets, the proposed network achieves a balance between computing speed and accuracy. Without additional processing and pretraining, it achieves 75.47% Mean IoU on the Cityscapes test dataset with only 29.96G Flops and a speed of 94 frames per second on a single RTX 2080Ti card. Code is available at https://github.com/favoMJ/FEENet.

Automated summary

This study proposes a feature extraction and enhancement network that achieves a balance between accuracy and computing speed in real-time semantic segmentation tasks.