Pruning Algorithms to Accelerate Convolutional Neural Networks for Edge Applications: A Survey

TL;DR

This survey reviews pruning techniques for CNNs, highlighting their motivations, strategies, advantages, drawbacks, and challenges to facilitate model deployment on edge devices.

Contribution

It provides a comprehensive overview of pruning algorithms, comparing different methods and discussing future challenges in CNN model compression for edge applications.

Findings

Pruning effectively reduces CNN model size and computation.

Different pruning strategies have varied advantages and limitations.

Challenges include maintaining accuracy and developing adaptive pruning methods.

Abstract

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.