AM-MulFSNet: A fast semantic segmentation network combining attention mechanism and multi-branch

In order to balance accuracy and real-time performance in semantic segmentation, this paper proposes a real-time semantic segmentation algorithm model based on attention mechanism and multi-branch feature fusion using Fast convolutional neural network model (Fast-SCNN). In this method, the spatial detail feature enhancement branch is introduced to enhance spatial detail features firstly. Then, through rational design of fusion module, the feature information of each branch is optimized to achieve better fusion of deep and shallow features. At the end of the feature fusion module, an adaptive feature enhancement focus module is introduced to capture the interdependence between remote pixels. The experimental results show that the proposed algorithm achieves 71.55% segmentation accuracy on Cityscapes dataset, the reasoning speed FPS is 97.6 frames/s, and the number of parameters is 1.39 M, which verifies the effectiveness of the network model constructed by the algorithm. Code is available at . This paper proposes a real-time semantic segmentation algorithm model based on attention mechanism and multi branch feature fusion. Firstly, spatial detail feature enhancement branches and convolutional attention modules are introduced to enhance the global feature representation of the network. At the same time, spatial detail enhancement features are aggregated with deep semantic features, and shallow features are weighted and fused together. Finally, an adaptive attention module is introduced to improve overall network performance. image