Fig. 5
From: U-Net combined with multi-scale attention mechanism for liver segmentation in CT images
The proposed RASM. Here, H, W, and C respectively represent the resolution height, width, and number of channels of the input low-level feature maps. C′ represents the number of channels for output feature maps. C″ represents the number of channels for output feature maps. The yellow square represents the convolution operation (where k represents the size of the convolution kernel, f represents the number of convolution kernels), and © represents the feature concatenation operation. ⊕ represents the feature addition operation