Fig. 4.
Filter kernels of size 11 × 11 pixels from convolutional layer, C1. Top: 64 nodes from original DCNN, bottom: 16 nodes from pruned DCNN. C1 layer is frozen during the first stage of transfer learning.
Filter kernels of size 11 × 11 pixels from convolutional layer, C1. Top: 64 nodes from original DCNN, bottom: 16 nodes from pruned DCNN. C1 layer is frozen during the first stage of transfer learning.