Remove to improve? Understanding CNN by pruning

The workhorses of CNNs are its filters, located at different layers and tuned to different features. Their responses are combined using weights obtained via network training. Training is aimed at optimal results for the entire training data, e.g., highest average classification accuracy. In this paper, we are interested in extending the current understanding of the roles played by the filters, their mutual interactions, and their relationship to classification accuracy. This is motivated by observations that the classification accuracy for some classes increases, instead of decreasing when some filters are pruned from a CNN. Additionally, the study showed that the classification accuracy of some classes from the target objects' set could be improved by removing the subset of filters with the least contribution to these classes.