关键词: 多尺度特征, 特征融合, 注意力机制, 语义分割

Abstract: Aiming at the problems  of low target segmentation rate and feeble correlation of image context feature information under multi-scale categories in image semantic segmentation, we proposed an image semantic segmentation model that fused attention mechanism and multi-scale features. The model used the improved  atrous spatial pyramid pooling to increase the segmentation of multi-scale targets, used the attention refinement module to capture context information to guide feature learning, and added feature fusion  based on attention mechanism to  supervise the learning of important channel features, guide the fusion of high-order and low-order features, so as to improve  the generalization capability of the model. The simulation results on the Cityscapes dataset show that the mean intersection over union of the model is 1.14% higher than that of DeepLab v3+, which proves that the model has good robustness.

Key words: multi-scale feature, feature fusion, attention mechanism, semantic segmentation