Retrain or not retrain? -- efficient pruning methods of deep CNN networks

Convolutional neural networks (CNN) play a major role in image processing\ntasks like image classification, object detection, semantic segmentation. Very\noften CNN networks have from several to hundred stacked layers with several\nmegabytes of weights. One of the possible methods to reduce complexity and\nmemory footprint is pruning. Pruning is a process of removing weights which\nconnect neurons from two adjacent layers in the network. The process of finding\nnear optimal solution with specified drop in accuracy can be more sophisticated\nwhen DL model has higher number of convolutional layers. In the paper few\napproaches based on retraining and no retraining are described and compared\ntogether.\n