Pruning Algorithms to Accelerate Convolutional Neural Networks for Edge Applications: A Survey
arXiv:2005.04275
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.
References in corpus (11)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Pruning Convolutional Neural Networks for Resource Efficient Inference
- AMC: AutoML for Model Compression and Acceleration on Mobile Devices
- Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures
- Pruning Filters for Efficient ConvNets
- An Entropy-based Pruning Method for CNN Compression
- Channel Gating Neural Networks
- Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks
- Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking
- Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization
Cited by in corpus (6)
- Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions
- On-Device Machine Learning: An Algorithms and Learning Theory Perspective
- Distributed Learning in Wireless Networks: Recent Progress and Future Challenges
- Two-level Group Convolution
- Deeplite Neutrino: An End-to-End Framework for Constrained Deep Learning Model Optimization
- Dense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace Offset