Pruning Algorithms to Accelerate Convolutional Neural Networks for Edge Applications: A Survey
It addresses the problem of deploying large CNN models on resource-constrained edge devices for researchers and practitioners, but it is incremental as it is a survey paper.
The paper surveys pruning algorithms as a model compression strategy to accelerate convolutional neural networks for edge applications, covering motivations, strategies, criteria, and major techniques without presenting new experimental results.
With the general trend of increasing Convolutional Neural Network (CNN) model sizes, model compression and acceleration techniques have become critical for the deployment of these models on edge devices. In this paper, we provide a comprehensive survey on Pruning, a major compression strategy that removes non-critical or redundant neurons from a CNN model. The survey covers the overarching motivation for pruning, different strategies and criteria, their advantages and drawbacks, along with a compilation of major pruning techniques. We conclude the survey with a discussion on alternatives to pruning and current challenges for the model compression community.