Awesome Pruning

A curated list of neural network pruning and related resources. Inspired by awesome-deep-vision, awesome-adversarial-machine-learning, awesome-deep-learning-papers and Awesome-NAS.

Please feel free to pull requests or open an issue to add papers.

Table of Contents

• Type of Pruning

• 2019 Venues

• 2018 Venues

• 2017 Venues

• 2016 Venues

• 2015 Venues

Type of Pruning

Type	F	W	Other
Explanation	Filter pruning	Weight pruning	other types

2019

Title	Venue	Type	Code
Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration	CVPR (Oral)	F	github
Towards Optimal Structured CNN Pruning via Generative Adversarial Learning	CVPR	F	github
Centripetal SGD for Pruning Very Deep Convolutional Networks with Complicated Structure	CVPR	F	github
On Implicit Filter Level Sparsity in Convolutional Neural Networks	CVPR	F	-
Structured Pruning of Neural Networks with Budget-Aware Regularization	CVPR	F	-
Importance Estimation for Neural Network Pruning	CVPR	F	-
Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search	CVPR	Other	github
Variational Convolutional Neural Network Pruning	CVPR	-	-
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks	ICLR (Best)	F	github
Rethinking the Value of Network Pruning	ICLR	F	github
Dynamic Channel Pruning: Feature Boosting and Suppression	ICLR	F	github
SNIP: Single-shot Network Pruning based on Connection Sensitivity	ICLR	F	github
Collaborative Channel Pruning for Deep Networks	ICML	F	-
Approximated Oracle Filter Pruning for Destructive CNN Width Optimization github	ICML	F	-
EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis4	ICML	W	github

2018

Title	Venue	Type	Code
Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers	ICLR	F	github
To prune, or not to prune: exploring the efficacy of pruning for model compression	ICLR	W	-
Discrimination-aware Channel Pruning for Deep Neural Networks	NIPS	F	github
Frequency-Domain Dynamic Pruning for Convolutional Neural Networks	NIPS	W	-
Amc: Automl for model compression and acceleration on mobile devices	ECCV	F	github
Data-Driven Sparse Structure Selection for Deep Neural Networks	ECCV	F	github
Coreset-Based Neural Network Compression	ECCV	F	github
Constraint-Aware Deep Neural Network Compression	ECCV	W	github
A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers	ECCV	W	github
PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning	CVPR	F	github
NISP: Pruning Networks using Neuron Importance Score Propagation	CVPR	F	-
CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization	CVPR	W	-
“Learning-Compression” Algorithms for Neural Net Pruning	CVPR	W	-
Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks	IJCAI	F	github

2017

Title	Venue	Type	Code
Pruning Filters for Efficient ConvNets	ICLR	F	github
Pruning Convolutional Neural Networks for Resource Efficient Inference	ICLR	W	github
Net-Trim: Convex Pruning of Deep Neural Networks with Performance Guarantee	NIPS	W	github
Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon	NIPS	W	github
Runtime Neural Pruning	NIPS	F	-
Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning	CVPR	F	-
ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression	ICCV	F	github
Channel pruning for accelerating very deep neural networks	ICCV	F	github
Learning Efficient Convolutional Networks Through Network Slimming	ICCV	F	github

2016

Title	Venue	Type	Code
Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding	ICLR (Best)	W	github
Dynamic Network Surgery for Efficient DNNs	NIPS	W	github

2015

Title	Venue	Type	Code
Learning both Weights and Connections for Efficient Neural Networks	NIPS	W	-

Related Repo

Awesome-model-compression-and-acceleration

EfficientDNNs

Embedded-Neural-Network

awesome-AutoML-and-Lightweight-Models

Model-Compression-Papers

knowledge-distillation-papers

Network-Speed-and-Compression