To address the problems of partial semantic information loss and low accuracy of boundary local-ization when convolutional neural networks are used for image semantic segmentation,this paper constructs a convolutional neural network by combining the attention mechanism and multi-scale features.The model firstly combines the multi-scale features extracted by the network based on the attention mechanism for weighting,then uses dilated convolution and global average pooling to aggregate the multi-scale target in-formation,and finally uses the boundary fine-grained feature extraction module to optimize the segmentation boundary.Experimental results on the multi-scale PASCAL VOC2012 and high-resolution Cityscapes data-sets show that the segmentation effect of the network in this paper is significantly better than that of the backbone ResNet-101,and the average cross-merge ratio is improved by 12.2 percentage points and 9.3 percentage points,respectively.
维普
万方数据