KiKi is the output achieved after the two convolution layers, and spatial loss of these convolutional operations is recovered by dense feature concatenation. The first aggregated rich, dense concatenated feature, A1Concat.AConcat.1, is the output of FiFi and KiKi given by Equation (2): A1Concat...
Each block has a different number of convolutional layers No booster block 5 pooling layers The number of trainable parameters is 29.46 M. There is no internal connectivity between the convolutional layers in the encoder and decoder. Residual connectivity is used. OR-Skip-Net [44] 16 ...