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 476–500 of 534 papers

Title	Date	Tasks	Status	Hype
Network Pruning via Transformable Architecture Search	May 23, 2019	Knowledge DistillationNetwork Pruning	CodeCode Available	0
EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis	May 15, 2019	Network Pruning	CodeCode Available	0
Network Pruning for Low-Rank Binary Indexing	May 14, 2019	Model CompressionNetwork Pruning	—Unverified	0
Towards Learning of Filter-Level Heterogeneous Compression of Convolutional Neural Networks	Apr 22, 2019	Network PruningNeural Architecture Search	CodeCode Available	0
Analysing Neural Network Topologies: a Game Theoretic Approach	Apr 17, 2019	Network Pruning	—Unverified	0
C2S2: Cost-aware Channel Sparse Selection for Progressive Network Pruning	Apr 6, 2019	channel selectionimage-classification	—Unverified	0
Progressive Stochastic Binarization of Deep Networks	Apr 3, 2019	BinarizationNetwork Pruning	CodeCode Available	0
Adversarial Robustness vs Model Compression, or Both?	Mar 29, 2019	Adversarial Robustnessmodel	CodeCode Available	0
FastDepth: Fast Monocular Depth Estimation on Embedded Systems	Mar 8, 2019	CPUDecoder	CodeCode Available	0
Single-shot Channel Pruning Based on Alternating Direction Method of Multipliers	Feb 18, 2019	General ClassificationNetwork Pruning	—Unverified	0
Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorization	Feb 5, 2019	Network PruningQuantization	CodeCode Available	0
DeepSZ: A Novel Framework to Compress Deep Neural Networks by Using Error-Bounded Lossy Compression	Jan 26, 2019	Network PruningNeural Network Compression	CodeCode Available	0
GASL: Guided Attention for Sparsity Learning in Deep Neural Networks	Jan 7, 2019	Model CompressionNetwork Pruning	CodeCode Available	0
A Main/Subsidiary Network Framework for Simplifying Binary Neural Network	Dec 11, 2018	Binarizationimage-classification	—Unverified	0
Few Sample Knowledge Distillation for Efficient Network Compression	Dec 5, 2018	Knowledge DistillationNetwork Pruning	CodeCode Available	0
Channel-wise pruning of neural networks with tapering resource constraint	Dec 4, 2018	Network PruningTransfer Learning	—Unverified	0
Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource Utilization	Dec 2, 2018	Network PruningNeural Architecture Search	CodeCode Available	0
Efficient Structured Pruning and Architecture Searching for Group Convolution	Nov 23, 2018	Domain AdaptationNetwork Pruning	CodeCode Available	0
Three Dimensional Convolutional Neural Network Pruning with Regularization-Based Method	Nov 19, 2018	Model CompressionNetwork Pruning	—Unverified	0
Convolutional Neural Network Pruning to Accelerate Membrane Segmentation in Electron Microscopy	Oct 23, 2018	Network PruningSegmentation	—Unverified	0
Dynamic parameter reallocation improves trainability of deep convolutional networks	Oct 20, 2018	Network Pruning	—Unverified	0
Dynamic Channel Pruning: Feature Boosting and Suppression	Oct 12, 2018	Model CompressionNetwork Pruning	CodeCode Available	1
Rethinking the Value of Network Pruning	Oct 11, 2018	Network PruningNeural Architecture Search	CodeCode Available	0
A Closer Look at Structured Pruning for Neural Network Compression	Oct 10, 2018	Network PruningNeural Network Compression	CodeCode Available	0
SNIP: Single-shot Network Pruning based on Connection Sensitivity	Oct 4, 2018	Image ClassificationNetwork Pruning	CodeCode Available	1

Show:10 25 50

← PrevPage 20 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