Network Pruning

Network Pruning is a popular approach to reduce a heavy network to obtain a light-weight form by removing redundancy in the heavy network. In this approach, a complex over-parameterized network is first trained, then pruned based on come criterions, and finally fine-tuned to achieve comparable performance with reduced parameters.

Source: Ensemble Knowledge Distillation for Learning Improved and Efficient Networks

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 501–525 of 534 papers

Title	Date	Tasks	Status	Hype
Clustering Convolutional Kernels to Compress Deep Neural Networks	Sep 1, 2018	ClusteringGeneral Classification	CodeCode Available	0
On-Device Neural Language Model Based Word Prediction	Aug 1, 2018	Automatic Speech Recognition (ASR)Language Modeling	CodeCode Available	0
Crossbar-aware neural network pruning	Jul 25, 2018	Network Pruning	—Unverified	0
Fast Convex Pruning of Deep Neural Networks	Jun 17, 2018	Network Pruning	CodeCode Available	0
âLearning-Compressionâ Algorithms for Neural Net Pruning	Jun 1, 2018	Model CompressionNetwork Pruning	—Unverified	0
CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization	Jun 1, 2018	image-classificationImage Classification	—Unverified	0
Channel Gating Neural Networks	May 29, 2018	Knowledge DistillationNetwork Pruning	CodeCode Available	1
Structured Pruning for Efficient ConvNets via Incremental Regularization	Apr 25, 2018	Network Pruning	CodeCode Available	0
A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers	Apr 10, 2018	Image ClassificationNetwork Pruning	CodeCode Available	0
A Quantization-Friendly Separable Convolution for MobileNets	Mar 22, 2018	Edge-computingGPU	CodeCode Available	0
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks	Mar 9, 2018	Network Pruning	CodeCode Available	1
Learning Sparse Structured Ensembles with SG-MCMC and Network Pruning	Mar 1, 2018	Language ModelingLanguage Modelling	—Unverified	0
Building Efficient ConvNets using Redundant Feature Pruning	Feb 21, 2018	Network Pruning	CodeCode Available	0
Efficient Sparse-Winograd Convolutional Neural Networks	Feb 18, 2018	Network Pruning	CodeCode Available	0
Attention-Based Guided Structured Sparsity of Deep Neural Networks	Feb 13, 2018	Network Pruning	CodeCode Available	0
Learning Compact Neural Networks with Regularization	Feb 5, 2018	Network Pruning	—Unverified	0
Recent Advances in Efficient Computation of Deep Convolutional Neural Networks	Feb 3, 2018	Network PruningQuantization	—Unverified	0
A relativistic extension of Hopfield neural networks via the mechanical analogy	Jan 5, 2018	Network Pruning	—Unverified	0
Structured Deep Neural Network Pruning via Matrix Pivoting	Dec 1, 2017	DiversityNetwork Pruning	—Unverified	0
NISP: Pruning Networks using Neuron Importance Score Propagation	Nov 16, 2017	Network Pruning	—Unverified	0
PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning	Nov 15, 2017	Continual LearningNetwork Pruning	CodeCode Available	1
NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm	Nov 6, 2017	Network Pruning	—Unverified	0
TraNNsformer: Neural network transformation for memristive crossbar based neuromorphic system design	Aug 26, 2017	Network Pruning	—Unverified	0
Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization	Jul 28, 2017	Bayesian OptimizationNetwork Pruning	—Unverified	0
SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks	May 23, 2017	Autonomous VehiclesNetwork Pruning	—Unverified	0

Show:10 25 50

← PrevPage 21 of 22Next →

All datasets ImageNet ImageNet - ResNet 50 - 90% sparsity CIFAR-100 CIFAR-10 MNIST

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	ResNet50-2.3 GFLOPs	Accuracy	78.79	—	Unverified
2	ResNet50-1.5 GFLOPs	Accuracy	78.07	—	Unverified
3	ResNet50 2.5 GFLOPS	Accuracy	78	—	Unverified
4	RegX-1.6G	Accuracy	77.97	—	Unverified
5	ResNet50 2.0 GFLOPS	Accuracy	77.7	—	Unverified
6	ResNet50-3G FLOPs	Accuracy	77.1	—	Unverified
7	ResNet50-2G FLOPs	Accuracy	76.4	—	Unverified
8	ResNet50-1G FLOPs	Accuracy	76.38	—	Unverified
9	TAS-pruned ResNet-50	Accuracy	76.2	—	Unverified
10	ResNet50	Accuracy	75.59	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Feather	Top-1 Accuracy	76.93	—	Unverified
2	Spartan	Top-1 Accuracy	76.17	—	Unverified
3	ST-3	Top-1 Accuracy	76.03	—	Unverified
4	AC/DC	Top-1 Accuracy	75.64	—	Unverified
5	CS	Top-1 Accuracy	75.5	—	Unverified
6	ProbMask	Top-1 Accuracy	74.68	—	Unverified
7	STR	Top-1 Accuracy	74.31	—	Unverified
8	DNW	Top-1 Accuracy	74	—	Unverified
9	GMP	Top-1 Accuracy	73.91	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	+U-DML*	Inference Time (ms)	675.56	—	Unverified
2	Dense	Accuracy	79	—	Unverified
3	AC/DC	Accuracy	78.2	—	Unverified
4	Beta-Rank	Accuracy	74.01	—	Unverified
5	TAS-pruned ResNet-110	Accuracy	73.16	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	TAS-pruned ResNet-110	Accuracy	94.33	—	Unverified
2	ShuffleNet – Quantised	Inference Time (ms)	23.15	—	Unverified
3	AlexNet – Quantised	Inference Time (ms)	5.23	—	Unverified
4	MobileNet – Quantised	Inference Time (ms)	4.74	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	FFN-ShapleyPruned	Avg #Steps	12.05	—	Unverified