Figure 3.

The structures of PSPNet and phase-fusion PSPNet. (a) represents the input image; (b) represents the feature extraction network, the feature extraction part of MobileNet or ResNet50; (c) represents the feature map extracted by the feature extraction network; (d) represents the pyramid pooling module; (e) represents the feature map output by the pyramid pooling module; (f) represents the output module; (g) represents the feature map formed by stage upsampling module; (h) represents the output image.