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 411–420 of 534 papers

Title	Date	Tasks	Status	Hype
Joint Device-Edge Inference over Wireless Links with Pruning	Mar 4, 2020	Feature CompressionGeneral Classification	—Unverified	0
Privacy-preserving Learning via Deep Net Pruning	Mar 4, 2020	Network PruningPrivacy Preserving	—Unverified	0
Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection	Mar 3, 2020	Network Pruning	CodeCode Available	1
HRank: Filter Pruning using High-Rank Feature Map	Feb 24, 2020	Network PruningVocal Bursts Intensity Prediction	CodeCode Available	1
HYDRA: Pruning Adversarially Robust Neural Networks	Feb 24, 2020	Network Pruning	CodeCode Available	1
On the Decision Boundaries of Neural Networks: A Tropical Geometry Perspective	Feb 20, 2020	Network Pruning	—Unverified	0
Performance Aware Convolutional Neural Network Channel Pruning for Embedded GPUs	Feb 20, 2020	Model CompressionNetwork Pruning	—Unverified	0
Structured Sparsification with Joint Optimization of Group Convolution and Channel Shuffle	Feb 19, 2020	Network Pruning	CodeCode Available	0
Knapsack Pruning with Inner Distillation	Feb 19, 2020	GPUKnowledge Distillation	CodeCode Available	1
Picking Winning Tickets Before Training by Preserving Gradient Flow	Feb 18, 2020	Network Pruning	CodeCode Available	1

Show:10 25 50

← PrevPage 42 of 54Next →

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