Fig. 2:

Overall architecture of GMIC (left) and architecture of ResNet-22 (right)¹. The patch map indicates positions of ROI patches (blue squares) on the input. In ResNet-22, we use c, s, and p to denote number of output channels, strides and size of padding. “ResBlock, c=32, d=2” denotes a vanilla ResBlock proposed in He et al. (2016b) with 32 output channels and a downsample skip connection that reduces the resolution with a factor of 2. In comparison to canonical ResNet architectures (He et al., 2016a), ResNet-22 has one more residual block and only a quarter of the filters in each convolution layer. Narrowing network width decreases the total number of hidden units which reduces GPU memory consumption.