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 426–450 of 534 papers

Title	Date	Tasks	Status	Hype
Filter Sketch for Network Pruning	Jan 23, 2020	Network Pruning	CodeCode Available	1
Pruning CNN's with linear filter ensembles	Jan 22, 2020	Network Pruning	—Unverified	0
A "Network Pruning Network" Approach to Deep Model Compression	Jan 15, 2020	Knowledge DistillationModel Compression	—Unverified	0
On Iterative Neural Network Pruning, Reinitialization, and the Similarity of Masks	Jan 14, 2020	Network Pruning	—Unverified	0
Quantisation and Pruning for Neural Network Compression and Regularisation	Jan 14, 2020	Network PruningNeural Network Compression	CodeCode Available	1
Resource-Efficient Neural Networks for Embedded Systems	Jan 7, 2020	Autonomous NavigationBIG-bench Machine Learning	—Unverified	0
Sparse Weight Activation Training	Jan 7, 2020	Image ClassificationNetwork Pruning	CodeCode Available	1
Discrimination-aware Network Pruning for Deep Model Compression	Jan 4, 2020	Face Recognitionimage-classification	CodeCode Available	1
Network Pruning by Greedy Subnetwork Selection	Jan 1, 2020	Network Pruning	—Unverified	0
MaskConvNet: Training Efficient ConvNets from Scratch via Budget-constrained Filter Pruning	Jan 1, 2020	Network Pruning	—Unverified	0
DBP: Discrimination Based Block-Level Pruning for Deep Model Acceleration	Dec 21, 2019	Network Pruning	—Unverified	0
Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning	Dec 18, 2019	Explainable Artificial Intelligence (XAI)Model Compression	CodeCode Available	0
Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion	Dec 18, 2019	Continual LearningDiversity	CodeCode Available	0
Winning the Lottery with Continuous Sparsification	Dec 10, 2019	Network PruningTicket Search	CodeCode Available	0
Explicit Group Sparse Projection with Applications to Deep Learning and NMF	Dec 9, 2019	Network Pruning	—Unverified	0
Ultrafast Photorealistic Style Transfer via Neural Architecture Search	Dec 5, 2019	Network PruningNeural Architecture Search	—Unverified	0
The Search for Sparse, Robust Neural Networks	Dec 5, 2019	Network Pruning	CodeCode Available	0
Quantum-Inspired Hamiltonian Monte Carlo for Bayesian Sampling	Dec 4, 2019	BIG-bench Machine LearningDenoising	CodeCode Available	0
AutoPrune: Automatic Network Pruning by Regularizing Auxiliary Parameters	Dec 1, 2019	Network Pruning	CodeCode Available	0
One-Shot Pruning of Recurrent Neural Networks by Jacobian Spectrum Evaluation	Nov 30, 2019	Network Pruning	—Unverified	0
Improving Feature Attribution through Input-specific Network Pruning	Nov 25, 2019	Network Pruning	—Unverified	0
Neural Network Pruning with Residual-Connections and Limited-Data	Nov 19, 2019	Knowledge DistillationNetwork Pruning	CodeCode Available	0
DARB: A Density-Aware Regular-Block Pruning for Deep Neural Networks	Nov 19, 2019	Model CompressionNetwork Pruning	—Unverified	0
What Do Compressed Deep Neural Networks Forget?	Nov 13, 2019	FairnessInterpretability Techniques for Deep Learning	CodeCode Available	0
Iteratively Training Look-Up Tables for Network Quantization	Nov 12, 2019	Network PruningQuantization	—Unverified	0

Show:10 25 50

← PrevPage 18 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