Skip to main content
Fig. 5 | Heritage Science

Fig. 5

From: Ancient mural segmentation based on a deep separable convolution network

Fig. 5

PSP-M workflow. The input image is subjected to deep separable convolution to form a feature map, which further undergoes maximum pooling and processing with the pyramid pooling module to obtain the semantic information of feature maps. Then, upsampling is performed for the image containing the semantic information using bilinear interpolation. Finally, feature maps of different hierarchies are spliced up to obtain the predicted image

Back to article page