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 291–300 of 534 papers

Title	Date	Tasks	Status	Hype
Connection Sensitivity Matters for Training-free DARTS: From Architecture-Level Scoring to Operation-Level Sensitivity Analysis	Jun 22, 2021	Computational EfficiencyNetwork Pruning	—Unverified	0
Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment Classification	Jun 21, 2021	Lifelong learningNetwork Pruning	CodeCode Available	0
Cogradient Descent for Dependable Learning	Jun 20, 2021	Image InpaintingImage Reconstruction	CodeCode Available	0
Network Pruning via Performance Maximization	Jun 19, 2021	Model CompressionNetwork Pruning	CodeCode Available	0
Sparse Training via Boosting Pruning Plasticity with Neuroregeneration	Jun 19, 2021	Network PruningSparse Learning	CodeCode Available	1
Heterogeneous Federated Learning using Dynamic Model Pruning and Adaptive Gradient	Jun 13, 2021	Federated LearningModel Compression	—Unverified	0
Self-Damaging Contrastive Learning	Jun 6, 2021	Contrastive LearningLinear evaluation	CodeCode Available	1
1xN Pattern for Pruning Convolutional Neural Networks	May 31, 2021	CPUNetwork Pruning	CodeCode Available	1
Dynamic Probabilistic Pruning: A general framework for hardware-constrained pruning at different granularities	May 26, 2021	image-classificationImage Classification	—Unverified	0
A Probabilistic Approach to Neural Network Pruning	May 20, 2021	Network Pruning	—Unverified	0

Show:10 25 50

← PrevPage 30 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