Carrying out CNN Channel Pruning in a White Box. (arXiv:2104.11883v4 [cs.CV] UPDATED)

Web: http://arxiv.org/abs/2104.11883

Channel Pruning has been long studied to compress CNNs, which significantly
reduces the overall computation. Prior works implement channel pruning in an
unexplainable manner, which tends to reduce the final classification errors
while failing to consider the internal influence of each channel. In this
paper, we conduct channel pruning in a white box. Through deep visualization of
feature maps activated by different channels, we observe that different
channels have a varying contribution to different categories in image
classification. Inspired by …

arxiv cnn cv